Abstract
A number of online communities and commercial apps exist to assist people with weight management. However, these systems are limited to logging and tracking meals or workouts without considering one's emotional state, which is known to have a strong impact on health (e.g., stress-related eating). To confirm the feasibility of monitoring emotion from personal logs such as online posts, we first conducted a Recurrent Neural Network (RNN) based sentiment analysis on 17,735 weight loss-related tweets and 200 posts from an online weight management community called FatSecret in comparisons to general tweets. The results suggest that we can infer one's emotion based on their written text and their progress in managing weight. Based on the findings, we propose EmoWei, a new weight management system that integrates users' emotions to provide personalized assistance to achieve their weight loss goals with minimum stress.
Original language | English |
---|---|
Title of host publication | Proceedings - 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science, IRI 2019 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 342-349 |
Number of pages | 8 |
ISBN (Electronic) | 9781728113371 |
DOIs | |
State | Published - Jul 2019 |
Event | 20th IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2019 - Los Angeles, United States Duration: 30 Jul 2019 → 1 Aug 2019 |
Publication series
Name | Proceedings - 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science, IRI 2019 |
---|
Conference
Conference | 20th IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2019 |
---|---|
Country/Territory | United States |
City | Los Angeles |
Period | 30/07/19 → 1/08/19 |
Bibliographical note
Publisher Copyright:© 2019 IEEE.
Keywords
- Diet
- Emotion
- Healthcare
- Mental health
- Sentiment analysis
- Social media
- Weight loss
- Weight management