Moment-to-moment mood change modelling in mobile mental health network

Tools

Alharbi, A, 2022. Moment-to-moment mood change modelling in mobile mental health network. PhD, Nottingham Trent University.

Preview

Text
Alanoud Alharbi 2022.pdf - Published version
Download (4MB) | Preview

Abstract

Human interests and behaviour change over time and often affected by multiple factors. In particular, human emotions, mood and its constituent processes change and interact over time. Therefore, modelling human behaviour should take into account the changes over time for customization and adaptation of systems to the users’ specific needs. Understanding and assessing the temporal dynamics of mood are critical for modelling human behaviour for both individuals and group of people who share similar habits, life style and personal circumstances. Thus, in order to construct a personalized recommendation for a given user, it is first necessary to have some knowledge about previous user interests and behaviours. However, the challenge of obtaining large-scale data on human emotions has left the most fundamental questions on emotions less explored: How do emotions vary across individuals, evolve over time, and are connected to social ties? We address these questions using a large-scale dataset of users that contains both their users’ interactions with momentary emotions and topical labels. Using this dataset, we identify patterns of human emotions on different levels, starting from the network level, group-level (cluster) and moving towards the user level. At the user-level, we identify how human emotions are distributed and vary over time. In particular, we model changes in mood using multi-level multimodal features including users’ sentimental status, engagement and linguistic queries. We also utilise language models to model and understand patterns of mood change. We model the changes of users’ mental states based on replies and responses to posts over time and predict future states. We find that the future mental states can be predicted with reasonable accuracy given users’ historical posts, current participation features. Our findings form a step forward towards better understand the interplay between user behaviour and mood change exhibited while interacting on mental health network and providing some interpretable summaries that can be used in the future by health experts and individuals and work on possible medical interventions together with clinical experts.

Item Type:	Thesis
Creators:	Alharbi, A.
Date:	January 2022
Rights:	The copyright in this work is held by the author. You may copy up to 5% of this work for private study, or personal, non-commercial research. Any re-use of the information contained within this document should be fully referenced, quoting the author, title, university, degree level and pagination. Queries or requests for any other use, or if a more substantial copy is required, should be directed to the author.
Divisions:	Schools > School of Science and Technology
Record created by:	Jeremy Silvester
Date Added:	06 Jul 2023 15:24
Last Modified:	06 Jul 2023 15:24
URI:	https://irep.ntu.ac.uk/id/eprint/49334