With its increasing use, social media has become a ubiquitous aspect of modern society. Social media users belong to a broad spectrum of age, ranging from teenage kids to old adults. The primary aim of this thesis is to compare and analyze two different approaches, Glove and Word2vec, utilized for the modeling of language within social media posts to assess the mental state of users. These two approaches along with supervised learning indicate whether or not a social media user demonstrates textual usage risk-factors of depression. This thesis analyzes two popular machine learning approaches for classifying users’ linguistic tendencies based on these language modeling approaches and tests the effectiveness of diagnosing individuals for depression, based on social network textual content. This thesis highlights the differences between the two modeling approaches and explores the causality that results in similar conclusions between both methodologies. Utilizing two different algorithms, Random Forest and Support Vector Machines, social media users were classified for exhibiting linguistic risk-factors of depression. This thesis compares the results between both modeling and machine learning algorithms.
|Commitee:||Tankelevich, Roman, Morales-Ponce, Oscar|
|School:||California State University, Long Beach|
|Department:||Computer Engineering and Computer Science|
|School Location:||United States -- California|
|Source:||MAI 81/3(E), Masters Abstracts International|
|Subjects:||Artificial intelligence, Computer science, Sociolinguistics|
|Keywords:||Deep learning, Machine learning, Random forest, Sentiment analysis, Support vector machines, Word vectorization|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be