Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms

This study aims to address the research gap in detecting depression from Arabic tweets using the PHQ-9 scale as a framework. The dataset collected was a set of 200,000 tweets from around 20,000 users. A team of psychologists and assistants used a user-based approach to label users as either depresse...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: ALSHEHHI, OMAR KHALID HAMAD (author)
منشور في: 2023
الموضوعات:
الوصول للمادة أونلاين:https://bspace.buid.ac.ae/handle/1234/2486
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1862980610609381376
author ALSHEHHI, OMAR KHALID HAMAD
author_facet ALSHEHHI, OMAR KHALID HAMAD
author_role author
dc.contributor.none.fl_str_mv Professor Sherief Abdallah
dc.creator.none.fl_str_mv ALSHEHHI, OMAR KHALID HAMAD
dc.date.none.fl_str_mv 2023-12
2024-01-24T08:15:45Z
2024-01-24T08:15:45Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv 20196024
https://bspace.buid.ac.ae/handle/1234/2486
dc.language.none.fl_str_mv en
dc.publisher.none.fl_str_mv The British University in Dubai (BUiD)
dc.subject.none.fl_str_mv social media, Arabic tweets, depression detection
dc.title.none.fl_str_mv Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
dc.type.none.fl_str_mv Thesis
description This study aims to address the research gap in detecting depression from Arabic tweets using the PHQ-9 scale as a framework. The dataset collected was a set of 200,000 tweets from around 20,000 users. A team of psychologists and assistants used a user-based approach to label users as either depressed or not. The data labelling and annotation process involved a user-based evaluation of the tweets to label users as either depressed or not, based on the two target variables of depressed_binary and depressed_multi. Users with scores between 0 and 6 were categorized as not depressed in the depressed_binary variable, while those with scores above six were classified as depressed. For the depressed_multi variable, users with scores ranging from 0 to 2 were labelled as not depressed, scores from 3 to 6 indicated mild depression, scores from 7 to 9 indicated moderate depression and scores of 10 or above represented high depression. Four machine learning models were employed in this study: HGB (Histogram Gradient Boost), GRU (Gated Recurrent Units), LSTM (Long Short-Term Memory), and SVM (Support Vector Machines). The findings revealed that the older models exhibited strong performance in binary classification, while the new models demonstrated competitive results. Future research should focus on exploring and developing newer deep learning models, such as HGB and GRU models, to enhance the accuracy and performance of depression detection in Arabic tweets. Future studies should also investigate strategies to account for the influence of different Arabic dialects and incorporate Arabic colloquialisms in depression detection models.
id budr_bbe73527a35d6d48f00f7c5da322fbd1
identifier_str_mv 20196024
language_invalid_str_mv en
network_acronym_str budr
network_name_str The British University in Dubai repository
oai_identifier_str oai:bspace.buid.ac.ae:1234/2486
publishDate 2023
publisher.none.fl_str_mv The British University in Dubai (BUiD)
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning AlgorithmsALSHEHHI, OMAR KHALID HAMADsocial media, Arabic tweets, depression detectionThis study aims to address the research gap in detecting depression from Arabic tweets using the PHQ-9 scale as a framework. The dataset collected was a set of 200,000 tweets from around 20,000 users. A team of psychologists and assistants used a user-based approach to label users as either depressed or not. The data labelling and annotation process involved a user-based evaluation of the tweets to label users as either depressed or not, based on the two target variables of depressed_binary and depressed_multi. Users with scores between 0 and 6 were categorized as not depressed in the depressed_binary variable, while those with scores above six were classified as depressed. For the depressed_multi variable, users with scores ranging from 0 to 2 were labelled as not depressed, scores from 3 to 6 indicated mild depression, scores from 7 to 9 indicated moderate depression and scores of 10 or above represented high depression. Four machine learning models were employed in this study: HGB (Histogram Gradient Boost), GRU (Gated Recurrent Units), LSTM (Long Short-Term Memory), and SVM (Support Vector Machines). The findings revealed that the older models exhibited strong performance in binary classification, while the new models demonstrated competitive results. Future research should focus on exploring and developing newer deep learning models, such as HGB and GRU models, to enhance the accuracy and performance of depression detection in Arabic tweets. Future studies should also investigate strategies to account for the influence of different Arabic dialects and incorporate Arabic colloquialisms in depression detection models.The British University in Dubai (BUiD)Professor Sherief Abdallah2024-01-24T08:15:45Z2024-01-24T08:15:45Z2023-12Thesisapplication/pdf20196024https://bspace.buid.ac.ae/handle/1234/2486enoai:bspace.buid.ac.ae:1234/24862024-03-01T06:09:39Z
spellingShingle Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
ALSHEHHI, OMAR KHALID HAMAD
social media, Arabic tweets, depression detection
title Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
title_full Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
title_fullStr Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
title_full_unstemmed Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
title_short Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
title_sort Detection of Depression in Arabic Social Media: A Comparison of Traditional and Modern Machine Learning Algorithms
topic social media, Arabic tweets, depression detection
url https://bspace.buid.ac.ae/handle/1234/2486