Smartphone-Based Estimation of a User Being in Company or Alone Based on Place, Time, and Activity

Exler, Anja; Braith, Marcel; Mincheva, Kristina; Schankin, Andrea; Beigl, Michael

doi:10.1007/978-3-319-90740-6_5

Cited by 9 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At the first level there are relatively simple objective factors that characterize the spatio-social context of a place: the number of people that are around the user, and activity, the type of activity carried in the place (e.g., working, eating, learning). These factors were found to affect social disturbance in previous studies [24,32,56]. The second level factors represent the perceived social norms related to the use of the place, norms that regulate the boundary between the personal territory and the public territory that surrounds the users [28].…”

Section: Research Modelmentioning

confidence: 92%

“…Vignette studies demonstrate that there is a social component to interruptibility. Users prefer not to be interrupted in places that are crowded [24,32], or preferred to be interrupted using a more private modality, such as a vibration rather than a ring [26].…”

Section: Introductionmentioning

confidence: 99%

“…In each place, users might interact with a different group of people, while carrying out different activities, and under various social norms. People's receptivity to interruptions is subject to type of place [33], the number of people around [24], and the character of the conversation and the activity that is being carried out in that space [55,56]. However, the current literature does not portray the role of social norms in perceived disturbance.…”

Section: Introductionmentioning

confidence: 99%

“…Schulze and Groh demonstrate that people's receptivity to interruptions is rooted in the social interaction in this place, and is subject to the character of the conversation, the activity that is being carried out, and other social factors [55,56]. In a lab study, Exler et al show that the activity of the user, the number of people around, and whether the user needs to focus play a role in determining interruptibility [24]. However, the number of people might not be enough to explain this difference.…”

Section: Introductionmentioning

confidence: 99%

“…The way people interpret their social context context is tightly related to the interaction between people in a particular physical space [24]. This interaction is then largely dependent on the norms that govern the spatial space and the social context of the interaction [27].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Can you Turn it Off?

Toch

Chassidim

Hatuka

2020

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Contemporary mobile devices continuously interrupt people with notifications in various and changing physical environments. As different places can have different social setting, understanding how disturbing an interruption might be to people around the user is not a straightforward task. To understand how users perceive disturbance in their social environment, we analyze the results of a 3-week user study with 50 participants using the experience sampling method and log analysis. We show that perceptions of disturbance are strongly related to the social norms surrounding the place, such as whether the place is considered private or public, even when controlling for the number of people around the user. Furthermore, users' perceptions of disturbance are also related to the activity carried out on the phone, and the subjective perceptions of isolation from other people in the space. We conclude the paper by discussing how our findings can be used to design new mobile devices that are aware of the social norms and their users' environmental context. CCS Concepts: • Human-centered computing → Empirical studies in HCI; Ubiquitous and mobile computing design and evaluation methods.

show abstract

Section: Research Modelmentioning

confidence: 92%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Can you Turn it Off?

Toch

Chassidim

Hatuka

2020

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

show abstract

Context recognition and ubiquitous computing in smart cities: a systematic mapping

et al. 2021

View full text Add to dashboard Cite

StressMon

Zakaria

Balan

Lee

2019

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Stress and depression are a common affliction in all walks of life. When left unmanaged, stress can inhibit productivity or cause depression. Depression can occur independently of stress. There has been a sharp rise in mobile health initiatives to monitor stress and depression. However, these initiatives usually require users to install dedicated apps or multiple sensors, making such solutions hard to scale. Moreover, they emphasise sensing individual factors and overlook social interactions, which plays a significant role in influencing stress and depression while being a part of a social system. We present StressMon, a stress and depression detection system that leverages single-attribute location data, passively sensed from the WiFi infrastructure. Using the location data, it extracts a detailed set of movement, and physical group interaction pattern features without requiring explicit user actions or software installation on client devices. These features are used in two different machine learning models to detect stress and depression. To validate StressMon, we conducted three different longitudinal studies at a university with different groups of students, totalling up to 108 participants. Our evaluation demonstrated StressMon detecting severely stressed students with a 96.01% True Positive Rate (TPR), an 80.76% True Negative Rate (TNR), and a 0.97 area under the ROC curve (AUC) score (a score of 1 indicates a perfect binary classifier) using a 6-day prediction window. In addition, StressMon was able to detect depression at 91.21% TPR, 66.71% TNR, and 0.88 AUC using a 15-day window. We end by discussing how StressMon can expand CSCW research, especially in areas involving collaborative practices for mental health management.

show abstract

Smartphone-Based Estimation of a User Being in Company or Alone Based on Place, Time, and Activity

Cited by 9 publications

References 19 publications

Can you Turn it Off?

Can you Turn it Off?

Context recognition and ubiquitous computing in smart cities: a systematic mapping

StressMon

Contact Info

Product

Resources

About