I-PAL: Mental Health Companion/ Tanya Faye S. Nivera and and four others

By:

Aliman, George B

Contributor(s):

Material type: Text

TextManila: Technological University of the Philippines, 2020Description: 141 pages : illustrations ; 30 cmContent type:

Media type:

Carrier type:

Subject(s):

LOC classification:

BTH TK 7816 A45 2019

Dissertation note: College of Engineering-- Bachelor of Science in Electronics Engineering, Technological University of the Philippines, 2020. Abstract: Social media is without a doubt a place where most people express their thoughts and feelings. Among the various social media currently there is, Twitter is where people are more vocal than in personal. A result from a study conducted by Child Mind Institute suggests that the more time you spent using social media, more likely you are depressed. Also, in recent years, cases of deaths relating to mental illness have become alarming, taking account for affected adults of 19%, 36% for adolescents and 16% for young kid. Given these facts, this paper proposed a model of sentiment analysis for predicting signs of depression from a Tweet (post from Twitter) using Natural Language Processing (NLP) and Logistic Regression. The said model will be integrated to Twitter's API and will stream for Tweets using APT search. Also, the sentiment analysis employed is applicable to English, Filipino and Taglish (Combination of English and Filipino language) languages. The system is capable of appeasing the emotions of identified mentally crisis Twitter users by sending motivational and uplifting quotes for the first reply. The bot will also intervene the user by sending mental health helplines or links for the second reply. The data of classified users with mental health crisis will be emailed to the mental health experts Based on the series of tests, the efficiency in predicting alarming tweets concerning mental health has increased due to the added training data and hit words to the system. The probability that the system could detect and reply alarming tweets concerning mental health was 92% based on Psychologist validation. Author's Abstract

Tags from this library: No tags from this library for this title. Log in to add tags.

Average rating: 0.0 (0 votes)

Holdings
Item type	Current library	Shelving location	Call number	Status	Notes	Date due	Barcode
Bachelor's Thesis COE	TUP Manila Library	Thesis Section-2nd floor	BTH TK 7816 A45 2019 (Browse shelf(Opens below))	Not for loan	For room use only		BTH0003468

Thesis (Undergraduate)

College of Engineering-- Bachelor of Science in Electronics Engineering, Technological University of the Philippines, 2020.

Social media is without a doubt a place where most people express their thoughts and feelings. Among the various social media currently there is, Twitter is where people are more vocal than in personal. A result from a study conducted by Child Mind Institute suggests that the more time you spent using social media, more likely you are depressed.
Also, in recent years, cases of deaths relating to mental illness have become alarming, taking account for affected adults of 19%, 36% for adolescents and 16% for young kid.
Given these facts, this paper proposed a model of sentiment analysis for predicting signs of depression from a Tweet (post from Twitter) using Natural Language Processing (NLP) and Logistic Regression. The said model will be integrated to Twitter's API and will stream for Tweets using APT search. Also, the sentiment analysis employed is applicable to English, Filipino and Taglish (Combination of English and Filipino language) languages.
The system is capable of appeasing the emotions of identified mentally crisis
Twitter users by sending motivational and uplifting quotes for the first reply. The bot will also intervene the user by sending mental health helplines or links for the second reply.
The data of classified users with mental health crisis will be emailed to the mental health
experts
Based on the series of tests, the efficiency in predicting alarming tweets concerning mental health has increased due to the added training data and hit words to
the system. The probability that the system could detect and reply alarming tweets
concerning mental health was 92% based on Psychologist validation. Author's Abstract

There are no comments on this title.

to post a comment.