Suicide ideation detection and response system for textual social media posts
Suicide is the fourth most common cause of mortality among youths. With t emergence of digital technology , media platforms as a "safe space " to i he ndividuals are increasingly using social express their suicidal tendencies this project focu supports real. As such, ses on developing a co...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2022
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/5015/ http://eprints.utar.edu.my/5015/1/2005778_LIM_YAN_QIAN.pdf |
| _version_ | 1848886304052346880 |
|---|---|
| author | Lim, Yan Qian |
| author_facet | Lim, Yan Qian |
| author_sort | Lim, Yan Qian |
| building | UTAR Institutional Repository |
| collection | Online Access |
| description | Suicide is the fourth most common cause of mortality among youths. With t emergence of digital technology , media platforms as a "safe space " to i he ndividuals are increasingly using social express their suicidal tendencies this project focu supports real. As such, ses on developing a comprehensive web application that time classification of tweets into three suicide risk categories and triggers a tailored crisis response that targets specific suicide risk levels. To that end, this project covers the en dtoend activities from model development, which uses Natural Language Processing and feature extraction techniques to improve the model’s classification performance, to its deployment on Flask web application framework for realtime monitoring and detect ion of tweets, and finally the initiation of proactive responses tailored to specific suicide risk levels. The methodology adopted for this project is Scrum methodology, which runs on 3 sprints. Results showed that the approach used significantly improved the classification performance when benchmarked with existing works. The model was integrated into the web system developed in this project and tested with random tweet samples of varying suicide risk. Overall, it was shown that the model maintained high p able to proactively erformance results and the system was trigger the correct response that addressed each suicide risk, which proves the efficacy of the model in realtime environment. |
| first_indexed | 2025-11-15T19:36:22Z |
| format | Final Year Project / Dissertation / Thesis |
| id | utar-5015 |
| institution | Universiti Tunku Abdul Rahman |
| institution_category | Local University |
| last_indexed | 2025-11-15T19:36:22Z |
| publishDate | 2022 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utar-50152022-12-26T14:06:27Z Suicide ideation detection and response system for textual social media posts Lim, Yan Qian QA76 Computer software Suicide is the fourth most common cause of mortality among youths. With t emergence of digital technology , media platforms as a "safe space " to i he ndividuals are increasingly using social express their suicidal tendencies this project focu supports real. As such, ses on developing a comprehensive web application that time classification of tweets into three suicide risk categories and triggers a tailored crisis response that targets specific suicide risk levels. To that end, this project covers the en dtoend activities from model development, which uses Natural Language Processing and feature extraction techniques to improve the model’s classification performance, to its deployment on Flask web application framework for realtime monitoring and detect ion of tweets, and finally the initiation of proactive responses tailored to specific suicide risk levels. The methodology adopted for this project is Scrum methodology, which runs on 3 sprints. Results showed that the approach used significantly improved the classification performance when benchmarked with existing works. The model was integrated into the web system developed in this project and tested with random tweet samples of varying suicide risk. Overall, it was shown that the model maintained high p able to proactively erformance results and the system was trigger the correct response that addressed each suicide risk, which proves the efficacy of the model in realtime environment. 2022 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/5015/1/2005778_LIM_YAN_QIAN.pdf Lim, Yan Qian (2022) Suicide ideation detection and response system for textual social media posts. Final Year Project, UTAR. http://eprints.utar.edu.my/5015/ |
| spellingShingle | QA76 Computer software Lim, Yan Qian Suicide ideation detection and response system for textual social media posts |
| title | Suicide ideation detection and response system for textual social media posts |
| title_full | Suicide ideation detection and response system for textual social media posts |
| title_fullStr | Suicide ideation detection and response system for textual social media posts |
| title_full_unstemmed | Suicide ideation detection and response system for textual social media posts |
| title_short | Suicide ideation detection and response system for textual social media posts |
| title_sort | suicide ideation detection and response system for textual social media posts |
| topic | QA76 Computer software |
| url | http://eprints.utar.edu.my/5015/ http://eprints.utar.edu.my/5015/1/2005778_LIM_YAN_QIAN.pdf |