Accepted papers

  1. Blue Mondays and Happy Meals: Investigating the impact of Contextual Factors on Mood States

    Nouran Abdalazim, Giovanni De Felice, Leonardo Alchieri, Lidia Alecci, Silvia Santini
    Università della Svizzera italiana (USI), Lugano, Switzerland

    Abstract: Mood plays a critical role in shaping cognition, memory, and well-being. While it is generally stable, it evolves gradually over time, “emotion inertia” phenomenon. Mood is also influenced by contextual factors, e.g, time, day, place, activity, and social context. In this study, we leverage the unique opportunity provided by the longitudinal and rich DiversityOne dataset, which includes self-reported mood and contextual information alongside smartphone sensor data collected over four weeks from 782 users across eight countries. We investigate temporal mood patterns and their associations with contextual information. Our experimental results provide quantitative evidence for the presence of the emotion inertia. Also, our findings confirm that the associations between mood and contextual factors, e.g., mood tends to be high around periods associated with meals (“Happy Meals”), and lower at the beginning of the week (“Blue Mondays”). Nevertheless, we observe cross-cultural variability in such associations. Finally, we show that integrating contextual features with mobility metrics derived from location sensor significantly enhances mood recognition performance w.r.t. using either feature set alone by up to six percentage points and achieving 74% balanced accuracy. These results highlight the promise of context-aware, passive sensing systems for end-to-end mood recognition with minimal reliance on self-reports.

  2. MakOne: Behavioural Data of University Students’ Smart Devices in Uganda

    Michael Kizito\(^1\), Ivan Kayongo\(^2\), Hawa Nyende\(^1\), Halimu Chongomweru\(^1\), Lillian Muyama\(^1\), Roy Alia Asiku\(^2\), Alice Mugisha\(^1\)

    \(^1\) Makerere University, Kampala, Uganda
    \(^2\) University of Trento, Trento, Italy

    Abstract: Understanding student behaviour in higher education is essential for improving academic performance, supporting mental wellbeing, and informing institutional policies. However, most existing behavioural datasets originate from Western institutions and overlook the unique socioeconomic and infrastructural contexts of African institutions, limiting the global applicability of resulting insights. This paper introduces MakOne, a novel multimodal dataset collected over six weeks from 72 students at Makerere University, Kampala, using iLog, a mobile sensing application. The dataset integrates passive smartphone sensor data—including location, physical activity, and screen usage—with ecological momentary assessments (EMAs) that capture students’ moods and daily routines. Designed to reflect the lived experiences of students in an African setting, MakOne offers a foundation for research in behaviour modeling, inclusive context-aware system design, mental health analytics, and culturally grounded educational technologies. It contributes a critical African perspective to the growing body of data-driven studies on student behaviour.

Back to top