Predicting Affective States from Screen Text Sentiment
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913477335973888 |
|---|---|
| author | Teng, Songyan Zhang, Tianyi D'Alfonso, Simon Kostakos, Vassilis |
| author_facet | Teng, Songyan Zhang, Tianyi D'Alfonso, Simon Kostakos, Vassilis |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12844 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Predicting Affective States from Screen Text Sentiment Teng, Songyan Zhang, Tianyi D'Alfonso, Simon Kostakos, Vassilis Human-Computer Interaction Artificial Intelligence 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. |
| title | Predicting Affective States from Screen Text Sentiment |
| topic | Human-Computer Interaction Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12844 |