Measuring mental well-being with mobile sensing has been an increasingly active research topic. Pervasiveness of smartphones combined with the convenience of mobile app distribution platforms (e.g., Google Play) provide a tremendous opportunity to reach out to millions of users. However, the studies at the confluence of mental health and mobile sensing have been longitudinally limited, controlled, or confined to a small number of participants. In this paper we report on what we believe is the largest longitudinal in-the-wild study of mood through smartphones. We describe an Android app to collect participants' self-reported moods and system triggered experience sampling data while passively measuring their physical activity, sociability, and mobility via their device's sensors. We report the results of a large-scale analysis of the data collected for about three years from ∼ 18, 000 users.The paper makes three primary contributions. First, we show how we used physical and software sensors in smartphones to automatically and accurately identify routines. Then, we demonstrate the strong correlation between these routines and users' personality, well-being perception, and other psychological variables. Finally, we explore predictability of users' mood using their passive sensing data. Our findings show that, especially for weekends, mobile sensing can be used to predict users' mood with an accuracy of about 70%. These results have the potential to impact the design of future mobile apps for mood/behavior tracking and interventions.

Experience sampling has long been the established method to sample people's mood in order to assess their mental state. Smartphones have started to be used as experience sampling tools for mental health state as they accompany individuals during their day and can therefore gather in-the-moment data. However, the granularity of the data needs to be traded off with the level of interruption these tools introduce on users' activities. As a consequence the data collected with this technique is often sparse. This has been obviated by the use of passive sensing in addition to mood reports, however this adds additional noise. In this paper we show that psychological traits collected through one-off questionnaires combined with passively collected sensing data (movement from the accelerometer and noise levels from the microphone) can be used to detect individuals whose general mood deviates from the common relaxed characteristic of the general population. By using the reported mood as a classification target we show how to design models that depend only on passive sensors and one-off questionnaires, without bothering users with tedious experience sampling. We validate our approach by using a large dataset of mood reports and passive sensing data collected in the wild with tens of thousands of participants, finding that the combination of these modalities has the best classification performance, and that passive sensing yields a +5% boost in accuracy. We also show that sensor data collected for the duration of a week performs better than when only using data collected for single days for this task. We discuss feature extraction techniques and appropriate classifiers for this kind of multimodal data, as well as overfitting shortcomings of using deep learning to handle static and dynamic features. We believe these findings have significant implications for mobile health applications that can benefit from the correct modeling of passive sensing along with extra user metadata.

Smartphones have started to be used as self reporting tools for mental health state as they accompany individuals during their days and can therefore gather temporally ne grained data. However, the analysis of self reported mood data oers challenges related to non-homogeneity of mood assessment among individuals due to the complexity of the feeling and the reporting scales, as well as the noise and sparseness of the reports when collected in the wild. In this paper, we propose a new end-to-end ML model inspired by video frame prediction and machine translation, that forecasts future sequences of mood from previous self-reported moods collected in the real world using mobile devices. Contrary to traditional time series forecasting algorithms, our multi-task encoder-decoder recurrent neural network learns patterns from dierent users, allowing and improving the prediction for users with limited number of self-reports. Unlike traditional feature-based machine learning algorithms, the encoder-decoder architecture enables to forecast a sequence of future moods rather than one single step. Meanwhile, multi-task learning exploits some unique characteristics of the data (mood is bi-dimensional), achieving better results than when training single-task networks or other classiers. Our experiments using a real-world dataset of 33, 000 user-weeks revealed that (i) 3 weeks of sparsely reported mood is the optimal number to accurately forecast mood, (ii) multi-task learning models both dimensions of mood-valence and arousal-with higher accuracy than separate or traditional ML models, and (iii) mood variability, personality traits and day of the week play a key role in the performance of our model. We believe this work provides psychologists and developers of future mobile mental health applications with a ready-to-use and eective tool for early diagnosis of mental health issues at scale.

Collaboration among scholars and institutions is progressively becoming essential to the success of research grant procurement and to allow the emergence and evolution of scientific disciplines. Our work focuses on analysing if the volume of collaborations of one author together with the relevance of his collaborators is somewhat related to his research performance over time. In order to prove this relation we collected the temporal distributions of scholars’ publications and citations from the Google Scholar platform and the co-authorship network (of Computer Scientists) underlying the well-known DBLP bibliographic database. By the application of time series clustering, social network analysis and non-parametric statistics, we observe that scholars with similar publications (citations) patterns also tend to have a similar centrality in the co-authorship network. To our knowledge, this is the first work that considers success evolution with respect to co-authorship.