@inproceedings{bhattacharjee2024understanding,

title = {Understanding the Role of Large Language Models in Personalizing and Scaffolding Strategies to Combat Academic Procrastination},

author = {Ananya Bhattacharjee and Yuchen Zeng and Sarah Yi Xu and Dana Kulzhabayeva and Minyi Ma and Rachel Kornfield and Syed Ishtiaque Ahmed and Alex Mariakakis and Mary Czerwinski and Anastasia Kuzminykh and Michael Liut and Joseph Jay Williams},

url = {https://www.microsoft.com/en-us/research/publication/understanding-the-role-of-large-language-models-in-personalizing-and-scaffolding-strategies-to-combat-academic-procrastination/},

year  = {2024},

date = {2024-05-01},

booktitle = {CHI 2024},

abstract = {Traditional interventions for academic procrastination often fail to capture the nuanced, individual-specific factors that underlie them. Large language models (LLMs) hold immense potential for addressing this gap by permitting open-ended inputs, including the ability to customize interventions to individuals' unique needs. However, user expectations and potential limitations of LLMs in this context remain underexplored. To address this, we conducted interviews and focus group discussions with 15 university students and 6 experts, during which a technology probe for generating personalized advice for managing procrastination was presented. Our results highlight the necessity for LLMs to provide structured, deadline-oriented steps and enhanced user support mechanisms. Additionally, our results surface the need for an adaptive approach to questioning based on factors like busyness. These findings offer crucial design implications for the development of LLM-based tools for managing procrastination while cautioning the use of LLMs for therapeutic guidance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{suh2023towards,

title = {Towards Successful Deployment of Wellbeing Sensing Technologies: Identifying Misalignments across Contextual Boundaries},

author = {Jina Suh and Javier Hernandez and Koustuv Saha and Kathy Dixon and Mehrab Bin Morshed and Esther Howe and Anna Kawakami and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/towards-successful-deployment-of-wellbeing-sensing-technologies-identifying-misalignments-across-contextual-boundaries/},

year  = {2023},

date = {2023-09-01},

booktitle = {ACII 2023 International Workshop on Affective Computing for Mental Wellbeing},

abstract = {Affective computing technologies have emerged as promising tools for supporting mental health and wellbeing but face deployment challenges in work and nonwork contexts due to misalignments in boundary preferences, data ownership, values and incentives, wellbeing definitions, and power dynamics. This paper presents a case study on the deployment of a just-in-time emotional support agent in the workplace, highlighting the five categories of misalignments that undermine the successful deployment of personal mental health support systems across these contextual boundaries. The identification and analysis of these misalignments contributes to a deeper understanding of the complexities and challenges faced when implementing affective computing systems for holistic mental health support. By emphasizing the importance of considering these misalignments in future research and development, this paper aims to contribute to the ongoing discourse on the effective and ethical deployment of affective computing technologies across work and nonwork contexts.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{swain2023focused,

title = {Focused Time Saves Nine: Evaluating Computer-Assisted Protected Time for Hybrid Information Work},

author = {Vedant Das Swain and Javier Hernandez and Brian Houck and Koustuv Saha and Jina Suh and Ahad Chaudhry and Tenny Cho and Wendy Guo and Shamsi Iqbal and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/focused-time-saves-nine-evaluating-computer-assisted-protected-time-for-hybrid-information-work/},

year  = {2023},

date = {2023-04-01},

booktitle = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems},

abstract = {Information workers often struggle to balance their time for a variety of activities like focused work, communication, and caring. This study analyzes the impact of a commercially available computer-assisted time protection intervention that automatically and preemptively schedules calendar time for self-determined activities. We analyzed the behaviors and self-reports of workers in two naturalistic studies. First, we studied 27 workers who were already using Computer-Assisted Protected Time (CAP time) and found that they mainly used it for focused work. Second, we analyzed the effect of CAP time as a randomized intervention on 89 workers who never had CAP time and found that those with it self-reported an increase in performance, job resources, and immersion. In both studies, workers with CAP time exhibited a rearrangement of activities leading to an overall reduction in work activity. This study highlights new opportunities for intelligent time-management interventions and the importance of protected time at work.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sefidgar2023lessons,

title = {Lessons Learned for Data-Driven Implementation Intentions with Mental Contrasting},

author = {Yasaman S. Sefidgar and Matthew Jörke and Jina Suh and Koustuv Saha and Shamsi Iqbal and Gonzalo Ramos and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/lessons-learned-for-data-driven-implementation-intentions-with-mental-contrasting/},

year  = {2023},

date = {2023-04-01},

booktitle = {CHI},

abstract = {Goal setting and realization are important but challenging. These challenges can be mitigated through effective application of behavior change realization techniques such as implementation intention and mental contrasting (IIMC). IIMC relies on identifying situations compromising desired behavior (i.e., obstacles) and creating action plans to handle those situations (i.e., identifying what, when, and where of actions to prevent or overcome the obstacles). We explore ways historical personal data can enhance the efficacy of IIMC application in the context of improving work-nonwork balance in a probing study with 16 information workers at a large technology company. We share lessons learned from this study that can help designers in further supporting goal realization with data, guide researchers interested in more formal studies of IIMC, and point the research community to important areas of future work on data-driven IIMC, particularly in the work context (e.g., the social dimensions of sense-making and planning).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nepal2023workplace,

title = {Workplace Rhythm Variability and Emotional Distress in Information Workers},

author = {Subigya Kumar Nepal and Javier Hernandez and Judith Amores and Mehrab Bin Morshed and Robert Lewis and Hemma Prafullchandra and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/workplace-rhythm-variability-and-emotional-distress-in-information-workers/},

year  = {2023},

date = {2023-04-01},

booktitle = {Extended Abstracts of the Conference on Human Factors in Computing Systems (CHI)},

pages = {1-8},

abstract = {Regularity in daily activities has been linked to positive well-being outcomes, but previous studies have mainly focused on clinical populations and traditional daily activities such as sleep and exercise. This research extends prior work by examining the regularity of both self-reported and digital activities of 49 information workers in a 4-week naturalistic study. Our findings suggest that greater variability in self-reported mood, job demands, lunch time, and sleep quality may be associated with increased stress, anxiety, and depression. However, when it comes to digital activity-based measures, greater variability in rhythm is associated with reduced emotional distress. This study expands our understanding of workers and the potential insights that can be gained from analyzing technology interactions and well-being.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hernandez2022deepfn,

title = {DeepFN: Towards Generalizable Facial Action Unit Recognition with Deep Face Normalization},

author = {Javier Hernandez and Daniel McDuff and Ognjen (Oggi) Rudovic and Alberto Fung and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/deepfn-towards-generalizable-facial-action-unit-recognition-with-deep-face-normalization/},

year  = {2022},

date = {2022-10-01},

booktitle = {International Conference on Affective Computing & Intelligent Interaction (ACII 2022)},

abstract = {Facial action unit recognition has many applications from market research to psychotherapy and from image captioning to entertainment. Despite its recent progress, deployment of these models has been impeded due to their limited generalization to unseen people and demographics. This work conducts an in-depth analysis of performance across several dimensions: individuals(40 subjects), genders (male and female), skin types (darker and lighter), and databases (BP4D and DISFA). To help suppress the variance in data, we use the notion of self-supervised denoising autoencoders to design a method for deep face normalization(DeepFN) that transfers facial expressions of different people onto a common facial template which is then used to train and evaluate facial action recognition models. We show that person-independent models yield significantly lower performance (55% average F1 and accuracy across 40 subjects) than person-dependent models (60.3%), leading to a generalization gap of 5.3%. However, normalizing the data with the newly introduced DeepFN significantly increased the performance of person-independent models (59.6%), effectively reducing the gap. Similarly, we observed generalization gaps when considering gender (2.4%), skin type (5.3%), and dataset (9.4%), which were significantly reduced with the use of DeepFN. These findings represent an important step towards the creation of more generalizable facial action unit recognition systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{morshed2022advancing,

title = {Advancing the Understanding and Measurement of Workplace Stress in Remote Information Workers from Passive Sensors and Behavioral Data},

author = {Mehrab Bin Morshed and Javier Hernandez and Daniel McDuff and Jina Suh and Esther Howe and Kael Rowan and Marah I Abdin and Gonzalo Ramos and Tracy Tran and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/advancing-the-understanding-and-measurement-of-workplace-stress-in-remote-information-workers-from-passive-sensors-and-behavioral-data/},

year  = {2022},

date = {2022-10-01},

booktitle = {International Conference on Affective Computing & Intelligent Interaction (ACII 2022)},

abstract = {Workplace stress has been increasing during the recent decades and has worsened by the unique demands imposed by COVID-19 and the new remote/hybrid work settings. High-stress working conditions can be detrimental to the health and wellness of workers and can lead to significant business costs in terms of productivity loss and medical costs. An important step towards managing stress involves finding comfortable ways to sense workers as well as recognizing stress as soon as it happens. This work explores the potential value of using pervasive sensors such as keyboards and webcams as well as behavioral data such as calendar and e-mail activity to passively assess individual stress levels of works in real-life. In particular, we collected a large corpus of such data from 46 remote information workers over one month and asked them to self-report their stress levels and other relevant factors several times a day. Analysis of the data demonstrates that passive sensors can effectively detect both triggers and manifestations of workplace stress and that having access to prior data of the worker is critical towards developing well-performing stress recognition models. Furthermore, we provide qualitative feedback capturing workers’ preferences in the context of workplace stress monitoring},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{howe2022design,

title = {Design of Digital Workplace Stress-Reduction Intervention Systems: Effects of Intervention Type and Timing},

author = {Esther Howe and Jina Suh and Mehrab Bin Morshed and Daniel McDuff and Kael Rowan and Javier Hernandez and Marah Ihab Abdin and Gonzalo Ramos and Tracy Tran and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/design-of-digital-workplace-stress-reduction-intervention-systems-effects-of-intervention-type-and-timing/},

year  = {2022},

date = {2022-04-01},

booktitle = {CHI 2022},

abstract = {Workplace stress-reduction interventions have produced mixed results due to engagement and adherence barriers. Leveraging technology to integrate such interventions into the workday may address these barriers and help mitigate the mental, physical, and monetary effects of workplace stress. To inform the design of a workplace stress-reduction intervention system, we conducted a four-week longitudinal study with 86 participants, examining the effects of intervention type and timing on usage, stress reduction impact, and user preferences. We compared three intervention types and two delivery timing conditions: Pre-scheduled (PS) by users and Just-in-time (JIT) prompted by the system-identified user stress-levels. We found JIT participants completed significantly more interventions than PS participants, but post-intervention and study-long stress reduction was not significantly different between conditions. Participants rated low-effort interventions highest, but high-effort interventions reduced the most stress. Participants felt JIT provided accountability but desired partial agency over timing. We present type and timing implications.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{hernandez2021guidelines,

title = {Guidelines for Assessing and Minimizing Risks of Emotion Recognition Applications},

author = {Javier Hernandez and Josh Lovejoy and Daniel McDuff and Jina Suh and Tim O'Brien and Arathi Sethumadhavan and Gretchen Greene and Rosalind Picard and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/guidelines-for-assessing-and-minimizing-risks-of-emotion-recognition-applications/},

year  = {2021},

date = {2021-10-01},

booktitle = {International Conference on Affective Computing & Intelligent Interaction (ACII 2021)},

abstract = {Society has witnessed a rapid increase in the adoption of commercial uses of emotion recognition. Tools that were traditionally used by domain experts are now being used by individuals who are often unaware of the technology's limitations and may use them in potentially harmful settings. The change in scale and agency, paired with gaps in regulation, urge the research community to rethink how we design, position, implement and ultimately deploy emotion recognition to anticipate and minimize potential risks. To help understand the current ecosystem of applied emotion recognition, this work provides an overview of some of the most frequent commercial applications and identifies some of the potential sources of harm. Informed by these, we then propose 12 guidelines for systematically assessing and reducing the risks presented by emotion recognition applications. These guidelines can help identify potential misuses and inform future deployments of emotion recognition.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mcduff2021do,

title = {Do affective cues validate behavioural metrics for search?},

author = {Daniel McDuff and Paul Thomas and Kael Rowan and Nick Craswell and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/do-affective-cues-validate-behavioural-metrics-for-search/},

year  = {2021},

date = {2021-07-01},

booktitle = {SIGIR 2021},

publisher = {ACM},

abstract = {Traces of searcher behaviour, such as query reformulation or clicks, are commonly used to evaluate a running search engine. The underlying expectation is that these behaviours are proxies for something more important, such as relevance, utility, or satisfaction. Affective computing technology gives us the tools to help confirm some of these expectations, by examining visceral expressive responses during search sessions. However, work to date has only studied small populations in laboratory settings and with a limited number of contrived search tasks. In this study, we analysed longitudinal, in-situ, search behaviours of 152 information workers, over the course of several weeks while simultaneously tracking their facial expressions. Results from over 20,000 search sessions and 45,000 queries allow us to observe that indeed affective expressions are consistent with, and complementary to, existing "click-based" metrics. On a query-level, searches that result in a short dwell time are associated with a decrease in smiles (expressions of "happiness") and that if a query is reformulated the results of the reformulation are associated with an increase in smiling—suggesting a positive outcome as people converge on the information they need. On a session-level, sessions that feature reformulations are more commonly associated with fewer smiles and more furrowed brows (expressions of "anger/frustration"). Similarly, sessions with short-dwell clicks are also associated with fewer smiles. These data provide an insight into visceral aspects of search experience and present a new dimension for evaluating engine performance.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{cao2021large,

title = {Large Scale Analysis of Multitasking Behavior During Remote Meetings},

author = {Hancheng Cao and Chia-Jung Lee and Shamsi Iqbal and Mary Czerwinski and Priscilla Wong and Sean Rintel and Brent Hecht and Jaime Teevan and Longqi Yang},

url = {https://www.microsoft.com/en-us/research/publication/large-scale-analysis-of-multitasking-behavior-during-remote-meetings/},

year  = {2021},

date = {2021-05-01},

booktitle = {CHI 2021},

organization = {ACM},

abstract = {Virtual meetings are critical for remote work because of the need for synchronous collaboration in the absence of in-person interactions. In-meeting multitasking is closely linked to people's productivity and wellbeing. However, we currently have limited understanding of multitasking in remote meetings and its potential impact. In this paper, we present what we believe is the most comprehensive study of remote meeting multitasking behavior through an analysis of a large-scale telemetry dataset collected from February to May 2020 of U.S. Microsoft employees and a 715-person diary study. Our results demonstrate that intrinsic meeting characteristics such as size, length, time, and type, significantly correlate with the extent to which people multitask, and multitasking can lead to both positive and negative outcomes. Our findings suggest important best-practice guidelines for remote meetings (e.g., avoid important meetings in the morning) and design implications for productivity tools (e.g., support positive remote multitasking).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{murali2021affectivespotlight,

title = {AffectiveSpotlight: Facilitating the Communication of Affective Responses from Audience Members during Online Presentations},

author = {Prasanth Murali and Javier Hernandez and Daniel McDuff and Kael Rowan and Jina Suh and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/affectivespotlight-facilitating-the-communication-of-affective-responses-from-audience-members-during-online-presentations/},

year  = {2021},

date = {2021-05-01},

booktitle = {CHI 2021},

abstract = {The ability to monitor audience reactions is critical when delivering presentations. However, current videoconferencing platforms offer limited solutions to support this. This work leverages recent advances in affect sensing to capture and facilitate communication of relevant audience signals. Using an exploratory survey (N=175), we assessed the most relevant audience responses such as confusion, engagement, and head-nods. We then implemented AffectiveSpotlight, a Microsoft Teams bot that analyzes facial responses and head gestures of audience members and dynamically spotlights the most expressive ones. In a within-subjects study with 14 groups (N=117),we observed that the system made presenters significantly more aware of their audience, speak for a longer period of time, and self-assess the quality of their talk more similarly to the audience members, compared to two control conditions (randomly-selected spotlight and default platform UI). We provide design recommendations for future affective interfaces for online presentations based on feedback from the study.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{samrose2021meetingcoach,

title = {MeetingCoach: An Intelligent Dashboard for Supporting Effective and Inclusive Meetings},

author = {Samiha Samrose and Daniel McDuff and Robert Sim and Jina Suh and Kael Rowan and Javier Hernandez and Sean Rintel and Kevin Moynihan and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/meetingcoach-an-intelligent-dashboard-for-supporting-effective-inclusive-meetings/},

year  = {2021},

date = {2021-05-01},

booktitle = {CHI 2021},

abstract = {Video-conferencing is essential for many companies, but its limitations in conveying social cues can lead to ineffective meetings. We present MeetingCoach, an intelligent post-meeting feedback dashboard that summarizes contextual and behavioral meeting information. Through an exploratory survey (N=120), we identified important signals (e.g., turn taking, sentiment) and used these insights to create a wireframe dashboard. The design was evaluated with in situ participants (N=16) who helped identify the components they would prefer in a post-meeting dashboard. After recording video-conferencing meetings of eight teams over four weeks, we developed an AI system to quantify the meeting features and created personalized dashboards for each participant. Through interviews and surveys (N=23), we found that reviewing the dash-board helped improve attendees’ awareness of meeting dynamics, with implications for improved effectiveness and inclusivity. Based on our findings, we provide suggestions for future feedback system designs of video-conferencing meetings.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thomas2021social,

title = {Social competence in conversational retrieval},

author = {Paul Thomas and Mary Czerwinski and Daniel McDuff and Nick Craswell},

url = {https://www.microsoft.com/en-us/research/publication/social-competence-in-conversational-retrieval/},

year  = {2021},

date = {2021-03-01},

booktitle = {Future Conversations},

abstract = {Conversational IR systems — here, meaning systems that work over multiple turns of natural language — are rapidly getting better at the basic functions of understanding searcher utterances, tracking context, and finding and presenting relevant information. However, conversation is much more than an exchange of facts: humans start learning conversational norms in utero, and unlike web UIs, conversational exchanges are laden with social signals. As humans, we cannot help but treat computers as social agents (Nass et al., 1994), so as developers and researchers we must be aware of social conventions.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thomas2020expressions,

title = {Expressions of style in information-seeking conversation with an embodied agent},

author = {Paul Thomas and Daniel McDuff and Mary Czerwinski and Nick Craswell},

url = {https://www.microsoft.com/en-us/research/publication/expressions-of-style-in-information-seeking-conversation-with-an-embodied-agent/},

year  = {2020},

date = {2020-07-01},

booktitle = {Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)},

publisher = {ACM Press},

abstract = {Past work in information-seeking conversation has demonstrated that people exhibit different conversational styles – for example, in word choice or prosody – that differences in style lead to poorer conversations, and that partners actively align their styles over time. One might assume that this would also be true for conversations with an artificial agent such as Cortana, Siri, or Alexa; and that agents should therefore track and mimic a user's style. We examine this hypothesis with reference to a lab study, where 24 participants carried out relatively long information-seeking tasks with an embodied conversational agent. The agent combined topical language models with a conversational dialogue engine, style recognition and alignment modules. We see that "style" can be measured in human-to-agent conversation, although it looks somewhat different to style in human-to-human conversation and does not correlate with self-reported preferences. There is evidence that people align their style to the agent, and that conversations run more smoothly if the agent detects, and aligns to, the human's style as well.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schroeder2020data-driven,

title = {Data-Driven Implications for Translating Evidence-Based Psychotherapies into Technology-Delivered Interventions},

author = {Jessica Schroeder and Jina Suh and Chelsey Wilks and Mary Czerwinski and Sean A. Munson and James Fogarty and Tim Althoff},

url = {https://www.microsoft.com/en-us/research/publication/data-driven-implications-for-translating-evidence-based-psychotherapies-into-technology-delivered-interventions/},

year  = {2020},

date = {2020-05-01},

booktitle = {EAI International Conference on Pervasive Computing Technologies for Healthcare},

abstract = {Mobile mental health interventions have the potential to reduce barriers and increase engagement in psychotherapy. However, most current tools fail to meet evidence-based principles. In this paper, we describe data-driven design implications for translating evidence-based interventions into mobile apps. To develop these design implications, we analyzed data from a month-long field study of an app designed to support dialectical behavioral therapy, a psychotherapy that aims to teach concrete coping skills to help people better manage their mental health. We investigated whether particular skills are more or less effective in reducing distress or emotional intensity. We also characterized how an individual's disorders, characteristics, and preferences may correlate with skill effectiveness, as well as how skill-level improvements correlate with study-wide changes in depressive symptoms. We then developed a model that predicted the effectiveness of specific skills. Based on our findings, we present design implications that emphasize the importance of considering different environmental, emotional, and personal contexts. Finally, we discuss promising future opportunities for mobile apps to better support evidence-based psychotherapies, including using machine learning algorithms to develop personalized and context-aware skill recommendations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kaur2020optimizing,

title = {Optimizing for Happiness and Productivity: Modeling Opportune Moments for Transitions and Breaks at Work},

author = {Harmanpreet Kaur and Alex C. Williams and Daniel McDuff and Mary Czerwinski and Jaime Teevan and Shamsi Iqbal},

url = {https://www.microsoft.com/en-us/research/publication/optimizing-for-happiness-and-productivity-modeling-opportune-moments-for-transitions-and-breaks-at-work/},

year  = {2020},

date = {2020-04-01},

booktitle = {ACM Conference on Human Factors in Computing Systems (CHI)},

organization = {ACM},

abstract = {Information workers perform jobs that demand constant multitasking, leading to context switches, productivity loss, stress, and unhappiness. Systems that can mediate task transitions and breaks have the potential to keep people both productive and happy. We explore a crucial initial step for this goal: finding opportune moments to recommend transitions and breaks without disrupting people during focused states. Using affect, workstation activity, and task data from a three-week field study (N = 25), we build models to predict whether a person should continue their task, transition to a new task, or take a break. The R2 values of our models are as high as 0.7, with only 15% error cases. We ask users to evaluate the timing of recommendations provided by a recommender that relies on these models. Our study shows that users find our transition and break recommendations to be well-timed, rating them as 86% and 77% accurate, respectively. We conclude with a discussion of the implications for intelligent systems that seek to guide task transitions and manage interruptions at work.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thomas2020theories,

title = {Theories of conversation for conversational IR},

author = {Paul Thomas and Mary Czerwinski and Daniel McDuff and Nick Craswell},

url = {https://www.microsoft.com/en-us/research/publication/theories-of-conversation-for-conversational-ir/},

year  = {2020},

date = {2020-03-01},

booktitle = {International Workshop on Conversational Approaches to Information Retrieval},

abstract = {Conversational information retrieval is a relatively new and fast-developing research area, but conversation itself has been well-studied for decades. Researchers have analysed linguistic phenomena such as structure and semantics but also para-linguistic features 

such as tone, body language and even the physiological states of interlocutors. We tend to treat computers as social agents – especially if they have some human-like features in their design – and so work from human-to-human conversation is highly relevant to how we 

think about the design of human-to-computer applications. In this position paper, we summarise some salient past work, focusing on social norms; structures; and affect, prosody and style. We also discuss some implications for research and design of conversational IR systems.},

note = {An extended version of this paper also appears as Thomas et al., ACM Trans. Info. Sys. 39(2), 2021: https://dl.acm.org/doi/pdf/10.1145/3439869.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{grover2020design,

title = {Design and Evaluation of Intelligent Agent Prototypes for Assistance with Focus and Productivity at Work},

author = {Ted Grover and Kael Rowan and Jina Suh and Daniel McDuff and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/design-and-evaluation-of-intelligent-agent-prototypes-forassistance-with-focus-and-productivity-at-work/},

year  = {2020},

date = {2020-03-01},

booktitle = {Intelligent User Interfaces (IUI)},

organization = {ACM},

abstract = {Current research on building intelligent agents for aiding with productivity and focus in the workplace is quite limited, despite the ubiquity of information workers across the globe. In our work, we present a productivity agent which helps users schedule and blockout time on their calendar to focus on important tasks, monitor and intervene with distractions, and reflect on their daily mood and goals in a single, standalone application. We created two different prototype versions of our agent: a text-based (TB) agent with a similar UI to a standard chatbot, and a more emotionally expressive virtual agent (VA) that employs a video avatar and the ability to detect and respond appropriately to users’ emotions. We evaluated these two agent prototypes against an existing product (control) condition through a three-week, within subjects study design with 40 participants, across different work roles in a large organization.We found that participants scheduled 134% more time with the TB prototype, and 110% more time with the VA prototype for focused tasks compared to the control condition. Users reported that they felt more satisfied and productive with the VA agent. However, the perception of anthropomorphism in the VA was polarized, with several participants suggesting that the human appearance was unnecessary. We discuss important insights from our work for the future design of conversational agents for productivity, well being, and focus in the workplace.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ghandeharioun2019emma,

title = {EMMA: An Emotion-Aware Wellbeing Chatbot},

author = {Asma Ghandeharioun and Daniel McDuff and Mary Czerwinski and Kael Rowan},

url = {https://www.microsoft.com/en-us/research/publication/emma-an-emotion-aware-wellbeing-chatbot/},

year  = {2019},

date = {2019-09-01},

booktitle = {International Conference on Affective Computing and Intelligent Interaction},

abstract = {The delivery of mental health interventions via ubiquitous devices has shown much promise. A conversational chatbot is a promising oracle for delivering appropriate just-in-time interventions. However, designing emotionally-aware agents, specially in this context, is under-explored. Furthermore, the feasibility of automating the delivery of just-in-time mHealth interventions via such an agent has not been fully studied. In this paper, we present the design and evaluation of EMMA (EMotion-Aware mHealth Agent) through a two-week long human-subject experiment with N=39 participants. EMMA provides emotionally appropriate micro-activities in an empathetic manner. We show that the system can be extended to detect a user's mood purely from smartphone sensor data. Our results show that our personalized machine learning model was perceived as likable via self-reports of emotion from users. Finally, we provide a set of guidelines for the design of emotion-aware bots for mHealth.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mcduff2019an,

title = {An End-to-End Conversational Style Matching Agent},

author = {Daniel McDuff and Mary Czerwinski and Rens Hoegen and Deepali Aneja},

url = {https://www.microsoft.com/en-us/research/publication/an-end-to-end-conversational-style-matching-agent/},

year  = {2019},

date = {2019-07-01},

booktitle = {IVA '19},

pages = {111-118},

publisher = {ACM},

organization = {ACM},

abstract = {We present an end-to-end voice-based conversational agent that is 

able to engage in naturalistic multi-turn dialogue and align with 

the interlocutor’s conversational style. The system uses a series of 

deep neural network components for speech recognition, dialogue 

generation, prosodic analysis and speech synthesis to generate 

language and prosodic expression with qualities that match those of the user. We conducted a user study (N=30) in which participants 

talked with the agent for 15 to 20 minutes, resulting in over 8 

hours of natural interaction data. Users with high consideration 

conversational styles reported the agent to be more trustworthy 

when it matched their conversational style. Whereas, users with 

high involvement conversational styles were indifferent. Finally, 

we provide design guidelines for multi-turn dialogue interactions 

using conversational style adaptation.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{costa2018regulating,

title = {Regulating Feelings During Interpersonal Conflicts by Changing Voice Self-perception},

author = {Jean Costa and Malte F. Jung and Mary Czerwinski and Francois Guimbretiere and Trinh Le and Tanzeem Choudhury},

url = {https://www.microsoft.com/en-us/research/publication/regulating-feelings-interpersonal-conflicts-changing-voice-self-perception/},

year  = {2018},

date = {2018-04-01},

booktitle = {CHI 2018},

publisher = {ACM},

edition = {CHI 2018},

abstract = {Emotions play a major role in how interpersonal conflicts unfold. Although several strategies and technological approaches have been proposed for emotion regulation, they often require conscious attention and effort. This often limits their efficacy in practice. In this paper, we propose a different approach inspired by self-perception theory: noticing that people are often reacting to the perception of their own behavior, we artificially change their perceptions to influence their emotions. We conducted two studies to evaluate the potential of this approach by automatically and subtly altering how people perceive their own voice. In one study, participants that received voice feedback with a calmer tone during relationship conflicts felt less anxious. In the other study, participants who listened to their own voices with a lower pitch during contentious debates felt more powerful. We discuss the implications of our findings and the opportunities for designing automatic and less perceptible emotion regulation systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{schoeder2018pocketskills,

title = {PocketSkills: A Conversational Mobile Web App to Support Dialectical Behavioral Therapy},

author = {Jessica Schoeder and Chelsey Wilks and Kael Rowan and Arturo Toledo and Ann Paradiso and Mary Czerwinski and Gloria Mark and Marsha M. Linehan},

url = {https://www.microsoft.com/en-us/research/publication/pocketskills-conversational-mobile-web-app-support-dialectical-behavioral-therapy/},

year  = {2018},

date = {2018-04-01},

booktitle = {In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI ’18)},

publisher = {ACM},

abstract = {Mental health disorders are a leading cause of disability worldwide. Although evidence-based psychotherapy is effective, engagement from such programs can be low. Mobile apps have the potential to help engage and support people in their therapy. We developed Pocket Skills, a mobile web app based on Dialectical Behavior Therapy (DBT). Pocket Skills teaches DBT via a conversational agent modeled on Marsha Linehan, who developed DBT. We examined the feasibility of Pocket Skills in a 4-week field study with 73 individuals enrolled in psychotherapy. After the study, participants reported decreased depression and anxiety and increased DBT skills use. We present a model based on qualitative findings of how Pocket Skills supported DBT. Pocket Skills helped participants engage in their DBT and practice and implement skills in their environmental context, which enabled them to see the results of using their DBT skills and increase their self-efficacy. We discuss the design implications of these findings for future mobile mental health systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{czerwinski2018regulating,

title = {Regulating Feelings During Interpersonal Conflicts by Changing Voice Self-perception},

author = {Mary Czerwinski and Jean Costa and Malte F. Jung and Francois Guimbretiere and Trinh Le and Tanzeem Choudhury},

url = {https://www.microsoft.com/en-us/research/publication/regulating-feelings-during-interpersonal-conflicts-by-changing-voice-self-perception/},

year  = {2018},

date = {2018-04-01},

booktitle = {CHI 2018},

publisher = {ACM},

organization = {ACM SIGCHI},

abstract = {Emotions play a major role in how interpersonal conflicts unfold. Although several strategies and technological approaches have been proposed for emotion regulation, they often require conscious attention and effort. This often limits their efficacy in practice. In this paper, we propose a different approach inspired by self-perception theory: noticing that people are often reacting to the perception of their own behavior, we artificially change their perceptions to influence their emotions. We conducted two studies to evaluate the potential of this approach by automatically and subtly altering how people perceive their own voice. In one study, participants that received voice feedback with a calmer tone during relationship conflicts felt less anxious. In the other study, participants who listened to their own voices with a lower pitch during contentious debates felt more powerful. We discuss the implications of our findings and the opportunities for designing automatic and less perceptible emotion regulation systems.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mark2018effects,

title = {Effects of Individual Differences in Blocking Workplace Distractions},

author = {Gloria Mark and Mary Czerwinski and Shamsi Iqbal},

url = {https://www.microsoft.com/en-us/research/publication/effects-individual-differences-blocking-workplace-distractions/},

year  = {2018},

date = {2018-04-01},

booktitle = {2018 ACM Conference on Human Factors in Computing Systems (CHI)},

publisher = {ACM},

abstract = {Information workers are experiencing ever-increasing online distractions in the workplace, and software to block distractions is becoming more popular. We conducted an exploratory field study with 32 information workers in their workplace using software to block online distractions for one week. We discovered that with online distractions blocked, participants assessed their focus and productivity to be significantly higher. Those who benefited most were those who reported being less in control of their work, associated with personality traits of lower Conscientiousness and Lack of Perseverence. Unexpectedly, those reporting higher control of work experienced a cost of higher workload with online distractions blocked. Those who reported the greatest increase in focus with distractions blocked were those who were more susceptible to social media distractions. Without distractions, people with higher control of work worked longer stretches without physical breaks, with consequently higher stress. We present design recommendations to promote focus for our observed coping behaviors.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thomas2018style,

title = {Style and alignment in information-seeking conversation},

author = {Paul Thomas and Mary Czerwinski and Daniel McDuff and Nick Craswell and Gloria Mark},

url = {https://www.microsoft.com/en-us/research/publication/style-and-alignment-in-information-seeking-conversation/},

year  = {2018},

date = {2018-03-01},

booktitle = {Proceedings of the Conference on Computer-Human Information Interaction and Retrieval},

publisher = {ACM},

edition = {Proceedings of the Conference on Computer-Human Information Interaction and Retrieval},

abstract = {Analysis of casual chit-chat indicates that differences in conversational style—the way things are said—can significantly impact a participants' impressions of the conversation and of each other. However, prior work has not systematically analyzed how important style is in task-oriented, information-seeking exchanges of the sort we might have with a conversational search agent. We examine recordings from the MISC data set, where pairs of "users" and "intermediaries" collaborate on information-seeking tasks, and look for indications of style which can be computed at scale. 

We find that stylistic markers identified by Tannen in casual chat do exist in information-seeking dialogue, and that participants can be arranged along a single stylistic dimension: "considerate" to "involved". This labelling for style needs no manual intervention. Furthermore, we find that there is no clear best style; but that differences in style, previously thought to impede communication, are only a problem for shorter tasks. This result is likely due to alignment of conversational style over the course of an interaction.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mcduff2017multimodal,

title = {Multimodal analysis of vocal collaborative search: A public corpus and results},

author = {Daniel McDuff and Paul Thomas and Mary Czerwinski and Nick Craswell},

url = {https://www.microsoft.com/en-us/research/publication/multimodal-analysis-of-vocal-collaborative-search-a-public-corpus-and-results/},

year  = {2017},

date = {2017-11-01},

booktitle = {Proceedings of the ACM International Conference on Multimodal Interaction},

publisher = {ACM},

edition = {Proceedings of the ACM International Conference on Multimodal Interaction},

abstract = {Intelligent agents have the potential to help with many tasks. Information seeking and voice-enabled search assistants are becoming very common. However, there remain questions as to the extent by which these agents should sense and respond to emotional signals. We designed a set of information seeking tasks and recruited participants to complete them using a human intermediary. In total we collected data from 22 pairs of individuals, each completing five search tasks. The participants could communicate only using voice, over a VoIP service. Using automated methods we extracted facial action, voice prosody and linguistic features from the audio-visual recordings. We analyzed the characteristics of these interactions that correlated with successful communication and understanding between the pairs. We found that those who were expressive in channels that were missing from the communication channel (e.g., facial actions and gaze) were rated as communicating poorly, being less helpful and understanding. Having a way of reinstating nonverbal cues into these interactions would improve the experience, even when the tasks are purely information seeking exercises. The dataset used for this analysis contains over 15 hours of video, audio and transcripts and reported ratings. It is publicly available for researchers at: http://aka.ms/MISCv1.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sano2017designing,

title = {Designing Opportune Stress Intervention Delivery Timing using Multi-modal Data},

author = {Akane Sano and Paul Johns and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/designing-opportune-stress-intervention-delivery-timing-using-multi-modal-data/},

year  = {2017},

date = {2017-10-01},

booktitle = {Proceedings of the Seventh International Conference on Affective Computing and Intelligent Interaction (ACII '17)},

pages = {346-353},

publisher = {IEEE},

abstract = {This paper describes a micro-stress intervention system for information office workers in the workplace, their responses to the interventions and machine learning models to predict the most opportune timing for providing the interventions. We studied 30 office workers for 10 days and examined their work patterns by monitoring their computer and application usage, sleep, activity, heart rate and its variability, as well as the history of micro-stress interventions provided through our desktop software. We analyzed temporal patterns of stress intervention acceptance/rejection and the relationships between their subjective and objective responses to the interventions and perceived work engagement, challenge and stress levels. We then developed machine learning models to predict better stress intervention delivery timing based on this multi-modal data. We found that features from computer and application usage, activity, heart rate variability and stress intervention history showed up to 80.0% accuracy in predicting good or bad intervention timing using a multi-kernel support vector machine algorithm. These findings could help practitioners design the most effective, just-in-time, closed-loop, stress interventions. To our knowledge, this is one of the first papers to review opportune stress interventions’ delivery timing research, which could have a big influence in the behavioral change technology domain.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{mark2017how,

title = {How Blocking Distractions Affects Workplace Focus and Productivity},

author = {Gloria Mark and Shamsi Iqbal and Mary Czerwinski},

url = {https://www.microsoft.com/en-us/research/publication/how-blocking-distractions-affects-workplace-focus-and-productivity/},

year  = {2017},

date = {2017-09-01},

booktitle = {UBICOMP/ISWC '17 Adjunct Proceedings},

publisher = {ACM},

edition = {UBICOMP/ISWC '17 Adjunct Proceedings},

abstract = {Information workers are faced with ever-increasing online distractions in the workplace. Website blockers are one solution toward preventing unwanted distractions. We conducted an in situ field study with 32 information workers in their workplace to test if the use of blocking software can increase focus and productivity by preventing non-work-related distractions. Participants worked for five days in a baseline condition and then worked five days where online distractions were blocked with software. We discovered that with blocking software, participants assessed their productivity significantly higher and could focus significantly longer. People who benefited the most from the software were those who were most distracted by social media. Interviews revealed individual differences in self-control in managing distractions. Resultant changes in work behaviors included switching from online distractions to physical breaks of leaving the office. An unexpected consequence of cutting off distractions for people with less self-control was that they were more focused and worked longer without taking breaks and therefore, experienced higher stress. We present design recommendations to promote focus for the variety of coping behaviors we observed.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{thomas2017misc,

title = {MISC: A data set of information-seeking conversations},

author = {Paul Thomas and Daniel McDuff and Mary Czerwinski and Nick Craswell},

url = {https://www.microsoft.com/en-us/research/publication/misc-data-set-information-seeking-conversations/},

year  = {2017},

date = {2017-08-01},

booktitle = {Proceedings of the 1st International Workshop on Conversational Approaches to Information Retrieval},

edition = {Proceedings of the 1st International Workshop on Conversational Approaches to Information Retrieval},

abstract = {Conversational interfaces to information retrieval systems, via software agents such as Siri or Cortana, are of commercial and research interest. To build or evaluate these software interfaces it is natural to consider how people act in the same role, but there is little public, fine-grained, data on interactions with intermediaries for web tasks. 

We introduce the Microsoft Information-Seeking Conversation data (MISC), a set of recordings of information-seeking conversations between human “seekers” and “intermediaries”. MISC includes audio and video signals; transcripts of conversation; affectual and physiological signals; recordings of search and other computer use; and post-task surveys on emotion, success, and effort. We hope that these recordings will support conversational retrieval interfaces both in engineering (how can we make “natural” systems?) and evaluation (what does a “good” conversation look like?).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{czerwinski2017machine,

title = {Machine learning for Precise Targeting of a Mobile Dialectical Behavior Therapy Skills Training Application},

author = {Mary Czerwinski and Chelsey Wilks and Kael Rowan and Ann Paradiso and Arturo Toledo and Daniel McDuff and Marsha Linehan},

url = {https://www.microsoft.com/en-us/research/publication/machine-learning-precise-targeting-mobile-dialectical-behavior-therapy-skills-training-application/},

year  = {2017},

date = {2017-04-01},

booktitle = {CHI 2017},

publisher = {ACM},

abstract = {A formative study of a mobile application for introducing skills related to Dialectical Behavior Therapy (DBT) is reviewed with an eye toward next iteration design. DBT is considered the gold standard for the treatment of suicide and borderline personality disorder, among other complex behavioral disorders. A multidisciplinary design team took licensed material from the creator of DBT, Marsha Linehan, and appropriated it for the mobile phone format and context of use. We walk through the design of the application including a conversational agent (“eMarsha”), videos of Dr. Linehan discussing therapeutic concepts and skills, and a module focusing on Mindfulness training. Initial evaluation of the app was encouraging with almost all users liking the flow and conversational user interface. In this paper, we focus on future work and the use of machine learning for precision psychology.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}