Predikcija depresije temeljem objava na društvenim mrežama

master's thesis

• Title (english): Prediction of Depression Using Social Media Posts
• Author: Monika Tenšić
• Mentor: Dijana Oreški (mentor); MBZ: 318615
• Committee member: Božidar Kliček; MBZ: 95426
• Granter: University of Zagreb; Faculty of Organization and Informatics; (Department of Information Systems Development); Varaždin
• Defense date and country: 2019-12-20, Croatia
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences; Organization and Informatics

Abstract

In this thesis, I use machine learning research for identifying signs of depression in social media posts. Depression and mental health problems, according to numerous studies, are evident in posts on social networks, which means we can use them to predict depression in individuals. In order to choose which type of algorithm is the best one for this application, comparison of different types of model training algorithms has been made. Data models used for training purposes were collected on online databases, created by other individuals. For algorithm development I used Python, and NTLK platform for training, testing and saving the model. Naive Bayes is used to create a classifier, which can detect signs of depression in the text by word analysis.

• Keywords: društvene mreže; strojno učenje; prediktivna analitika
• Language: croatian
• URN:NBN: urn:nbn:hr:211:252678
• Study programme: Title: Information and Programming Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra informatike (magistar/magistra informatike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2020-04-27 07:21:46