Mood modeling: accuracy depends on active logging and reflection

Springer, Aaron; Hollis, Victoria; Whittaker, Steve

doi:10.1007/s00779-018-1123-8

Cited by 19 publications

(15 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, people need to be able to reflect on how their mental health fluctuates [33] and this can be problematic. Peoples' appraisal of emotional events are subjective to change of time, especially if measured with a delay [34].…”

Section: Limitationsmentioning

confidence: 99%

The Bittersweet Effects of COVID-19 on Mental Health: Results of an Online Survey among a Sample of the Dutch Population Five Weeks after Relaxation of Lockdown Restrictions

Gijzen

Shields-Zeeman

Kleinjan

et al. 2020

IJERPH

View full text Add to dashboard Cite

Previous research shows that crises can have both negative and positive mental health effects on the population. The current study explored these effects in the context of the COVID-19 pandemic after relaxation of governmental measures. An online survey was administered among a representative sample of the Dutch population (n = 1519) in June 2020, ten weeks after the peak of COVID-19 had passed, and five weeks after restrictions were relaxed. Participants were asked about mental health, adverse events during COVID-19, and about any positive effects of the pandemic. Most participants (80%, n = 1207) reported no change in mental health since the COVID-19 pandemic. This was also the case among respondents who had experienced an adverse event. Protective factors of mental health were being male and high levels of positive mental well-being. Risk factors were emotional loneliness and the experience of adverse life events. Social loneliness was positively associated with stable mental health, stressing the importance of meaningful relationships. Note that 58% of participants reported positive effects of the pandemic, the most common of which were rest, working from home, and feeling more socially connected. In summary, 10 weeks after the start of the crisis, and 5 weeks after relaxation of the restrictions, most people remained stable during the crisis, and were even able to report positive effects.

show abstract

Section: Limitationsmentioning

confidence: 99%

The Bittersweet Effects of COVID-19 on Mental Health: Results of an Online Survey among a Sample of the Dutch Population Five Weeks after Relaxation of Lockdown Restrictions

Gijzen

Shields-Zeeman

Kleinjan

et al. 2020

IJERPH

View full text Add to dashboard Cite

show abstract

“…Future designs could support mood regulation strategies that focus on current mood states, by providing insights about mood patterns and suggesting methods for improving mood (e.g. EmotiCal [64]). Automatic behavioral data sampling using sensors and existing phone data could also be used to track and predict low moods and provide more timely interventions [23].…”

Section: Context Of Usementioning

confidence: 99%

The Experience of Guided Online Therapy: A Longitudinal, Qualitative Analysis of Client Feedback in a Naturalistic RCT

Jardine

Earley

Richards

et al. 2020

Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Internet-delivered Cognitive Behavioural Therapy (iCBT) is an effective treatment for depression and anxiety disorders. However longitudinal qualitative research into the client's subjective experience of this form of treatment 'in the wild' is relatively scarce. We present an analysis of secondary outcomes in a naturalistic RCT conducted within the UK's Improving Access to Psychological Therapies programme. We evaluated clients' expectations, experience, and context of usage of iCBT, across three timepoints. Results are discussed in terms of the creation of a therapeutic space online, the impact of hope, expectations and personal factors on the therapeutic experience, iCBT as "therapy on the go" and developing skills for life. While iCBT on the whole provides a positive, supportive and therapeutic experience for clients, the study identified managing expectations, polarized preferences, momentary help-seeking and longterm support as important aspects of the experience to consider in future design.

show abstract

“…One suggestion is that these different effects arise from the expectation violation that a user experiences. Expectation violation occurs when the system behaves in a way that a user did not anticipate [43,78,79,80]. Ideally transparency should build user confidence in a system, whether or not the user is experiencing expectation violation [43,80].…”

Section: Transparencymentioning

confidence: 99%

“…Models were trained on text gathered from the EmotiCal deployment [38,79]. In that deployment, users reported on their activities and emotions over several weeks by writing textual entries about daily experiences and directly evaluating their mood in relation to those experiences.…”

Section: Machine Learning Modelmentioning

confidence: 99%

Progressive Disclosure

Springer

Whittaker

2020

ACM Trans. Interact. Intell. Syst.

Self Cite

View full text Add to dashboard Cite

It is essential that users understand how algorithmic decisions are made, as we increasingly delegate important decisions to intelligent systems. Prior work has often taken a techno-centric approach, focusing on new computational techniques to support transparency. In contrast, this article employs empirical methods to better understand user reactions to transparent systems to motivate user-centric designs for transparent systems. We assess user reactions to transparency feedback in four studies of an emotional analytics system. In Study 1, users anticipated that a transparent system would perform better but unexpectedly retracted this evaluation after experience with the system. Study 2 offers an explanation for this paradox by showing that the benefits of transparency are context dependent. On the one hand, transparency can help users form a model of the underlying algorithm's operation. On the other hand, positive accuracy perceptions may be undermined when transparency reveals algorithmic errors. Study 3 explored real-time reactions to transparency. Results confirmed Study 2, in showing that users are both more likely to consult transparency information and to experience greater system insights when formulating a model of system operation. Study 4 used qualitative methods to explore real-time user reactions to motivate transparency design principles. Results again suggest that users may benefit from initially simplified feedback that hides potential system errors and assists users in building working heuristics about system operation. We use these findings to motivate new progressive disclosure principles for transparency in intelligent systems and discuss theoretical implications. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing design and evaluation methods; • Social and professional topics → Government technology policy; • Human-centered computing → HCI theory, concepts and models; Interaction paradigms; Empirical studies in HCI;

show abstract

Mood modeling: accuracy depends on active logging and reflection

Cited by 19 publications

References 45 publications

The Bittersweet Effects of COVID-19 on Mental Health: Results of an Online Survey among a Sample of the Dutch Population Five Weeks after Relaxation of Lockdown Restrictions

The Bittersweet Effects of COVID-19 on Mental Health: Results of an Online Survey among a Sample of the Dutch Population Five Weeks after Relaxation of Lockdown Restrictions

The Experience of Guided Online Therapy: A Longitudinal, Qualitative Analysis of Client Feedback in a Naturalistic RCT

Progressive Disclosure

Contact Info

Product

Resources

About