000			02843nam a22003377a 4500
003			OSt
005			20231211160120.0
008			231211b |||||||| |||| 00| 0 eng d
040			_aTUPM _beng _c- _d- _erda
050			_aBTH TK 7816 _bA45 2019
100			_aAliman, George B.
245			_aI-PAL: Mental Health Companion/ _cTanya Faye S. Nivera and and four others
264			_aManila: _bTechnological University of the Philippines, _c2020.
300			_a141 pages : _billustrations ; _c30 cm.
336			_2rdacontent
337			_2rdamedia
338			_2rdacarrier
500			_aThesis (Undergraduate)
502			_aCollege of Engineering-- _bBachelor of Science in Electronics Engineering, _cTechnological University of the Philippines, _d2020.
520	3		_aSocial 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. _bAuthor's Abstract
650			_aNatural language processing (Computer science)
650			_aHuman-computer interaction
650			_aProgramming languages (Electronic computers)
700			_aAliman, George B.
700			_aNivera, Tanya Faye S.
700			_aOlazo, Jensine Charmille A
700			_aRamos, Daisy Jane P.
700			_aSanchez, Chris Danielle B.
942			_2lcc _cBTH COE _n0
999			_c28377 _d28377