Predicting Affective States from Screen Text Sentiment
This work addresses the problem of improving affect prediction for mental health monitoring by incorporating textual data from smartphones, though it is incremental as it builds on existing methods.
The study tackled predicting affective states from screen text sentiment by analyzing data from a digital phenotyping study of Australian university students, finding that multi-shot prompting with an LLM substantially outperformed linear regression and zero-shot prompting.
The proliferation of mobile sensing technologies has enabled the study of various physiological and behavioural phenomena through unobtrusive data collection from smartphone sensors. This approach offers real-time insights into individuals' physical and mental states, creating opportunities for personalised treatment and interventions. However, the potential of analysing the textual content viewed on smartphones to predict affective states remains underexplored. To better understand how the screen text that users are exposed to and interact with can influence their affects, we investigated a subset of data obtained from a digital phenotyping study of Australian university students conducted in 2023. We employed linear regression, zero-shot, and multi-shot prompting using a large language model (LLM) to analyse relationships between screen text and affective states. Our findings indicate that multi-shot prompting substantially outperforms both linear regression and zero-shot prompting, highlighting the importance of context in affect prediction. We discuss the value of incorporating textual and sentiment data for improving affect prediction, providing a basis for future advancements in understanding smartphone use and wellbeing.