No abstract

A person seeking another person's attention is normally able to quickly assess how interruptible the other person currently is. Such assessments allow behavior that we consider natural, socially appropriate, or simply polite. This is in sharp contrast to current computer and communication systems, which are largely unaware of the social situations surrounding their usage and the impact that their actions have on these situations. If systems could model human interruptibility, they could use this information to negotiate interruptions at appropriate times, thus improving human computer interaction.This article presents a series of studies that quantitatively demonstrate that simple sensors can support the construction of models that estimate human interruptibility as well as people do. These models can be constructed without using complex sensors, such as vision-based techniques, and therefore their use in everyday office environments is both practical and affordable. Although currently based on a demographically limited sample, our results indicate a substantial opportunity for future research to validate these results over larger groups of office workers. Our results also motivate the development of systems that use these models to negotiate interruptions at socially appropriate times.

A person seeking someone else's attention is normally able to quickly assess how interruptible they are. This assessment allows for behavior we perceive as natural, socially appropriate, or simply polite. On the other hand, today's computer systems are almost entirely oblivious to the human world they operate in, and typically have no way to take into account the interruptibility of the user. This paper presents a Wizard of Oz study exploring whether, and how, robust sensor-based predictions of interruptibility might be constructed, which sensors might be most useful to such predictions, and how simple such sensors might be.The study simulates a range of possible sensors through human coding of audio and video recordings. Experience sampling is used to simultaneously collect randomly distributed self-reports of interruptibility. Based on these simulated sensors, we construct statistical models predicting human interruptibility and compare their predictions with the collected self-report data. The results of these models, although covering a demographically limited sample, are very promising, with the overall accuracy of several models reaching about 78%. Additionally, a model tuned to avoiding unwanted interruptions does so for 90% of its predictions, while retaining 75% overall accuracy.

We consider why and how women track their menstrual cycles, examining their experiences to uncover design opportunities and extend the field's understanding of personal informatics tools. To understand menstrual cycle tracking practices, we collected and analyzed data from three sources: 2,000 reviews of popular menstrual tracking apps, a survey of 687 people, and follow-up interviews with 12 survey respondents. We find that women track their menstrual cycle for varied reasons that include remembering and predicting their period as well as informing conversations with healthcare providers. Participants described six methods of tracking their menstrual cycles, including use of technology, awareness of their premenstrual physiological states, and simply remembering. Although women find apps and calendars helpful, these methods are ineffective when predictions of future menstrual cycles are inaccurate. Designs can create feelings of exclusion for gender and sexual minorities. Existing apps also generally fail to consider life stages that women experience, including young adulthood, pregnancy, and menopause. Our findings encourage expanding the field's conceptions of personal informatics.

Patient-generated data is increasingly common in chronic disease care management. Smartphone applications and wearable sensors help patients more easily collect health information. However, current commercial tools often do not effectively support patients and providers in collaboration surrounding these data. This paper examines patient expectations and current collaboration practices around patient-generated data. We survey 211 patients, interview 18 patients, and re-analyze a dataset of 21 provider interviews. We find that collaboration occurs in every stage of self-tracking and that patients and providers create boundary negotiating artifacts to support the collaboration. Building upon current practices with patient-generated data, we use these theories of patient and provider collaboration to analyze misunderstandings and privacy concerns as well as identify opportunities to better support these collaborations. We reflect on the social nature of patient-provider collaboration to suggest future development of the stage-based model of personal informatics and the theory of boundary negotiating artifacts.