000			03410ntm a2200337 i 4500
999			_c100858 _d100864
003			MY-KuUP
005			20251125110900.0
006			t||||fr|||| 000 0
007			ta
008			240529t20222022my a|||fr|||| 000 0 eng d
020			_aTHE0009860 (Local) _qHardback
040			_aUMPSA _beng _cUMP _erda
090			_aPSM .S93 2022 r Bc
100	1		_aSiti Nur Syamimi Binti Mat Zain, _eauthor.
245	1	0	_aCustomer sentiment analysis through social media feedback / _cSiti Nur Syamimi Binti Mat Zain
264		1	_aKuantan, Pahang : _bUMPSA, _c2022
264		4	_c©2022
300			_axi, 64 pages : _billustrations ; _c _e1 CD-ROM
336			_2rdacontent _atext
337			_2rdamedia _aunmediated
338			_2rdacarrier _avolume
347			_2rda _atext file _bPDF
500			_aCentre for Mathematical Sciences
502			_aBachelor of Applied Science in Data Analytics with Honours -- Universiti Malaysia Pahang – 2022
504			_aIncludes bibliographical references
520	3		_aCustomer sentiment analysis is an automated way of detecting sentiments in online interactions in order to assess customer opinions about a product, brand or service. It assists companies in gaining insights and efficiently responding to their customers. Social media, forums, blogs and the web have become channels for people to voice their opinions openly on a variety of discussion topics making it an ideal domain to utilise customer sentiment analysis. This study presents a machine learning approach to analyse how sentiment analysis detects positive and negative feedback about TM ONE products. Customer feedback data were taken from Twitter through Streaming API (Application Programming Interface), where Tweets are retrieved in real time based on search terms, time, users and likes. Responses from the twitter API are parsed into tables and stored in a CSV file. All of these processes were done in Python via Jupyter Notebook. Then, the analysis continued with the pre-processing stage for cleaning where the correct data can be extracted as much as possible from the text by converting noise from high-dimensional features to low-dimensional spaces. Based on the analysis, it was found that there was no negative sentiment from TM ONE customers. The data were then split into training and testing to be tested on the three different supervised learning algorithms used in this study which are Support Vector Machine, Random Forest, and Naïve Bayes. Lasty, the performance of each model was compared to select the most accurate model and from the analysis, it can be concluded that Support Vector Machine gives the best performance in terms of accuracy, mean squared error, root mean squared error and area under ROC curve. Regarding the results of customer sentiment analysis, some suggestions that can be utilized to improve this study are to conduct customer sentiment analysis by obtaining customer feedback data through Facebook, Instagram, Tik Tok, Web and forums. In addition, the performance of the customer sentiment analysis model can be enhanced by using deep learning methods. Last but not least, this sentiment analysis study can also be applied to texts written in Malay language.
610	2	0	_aCentre for Mathematical Sciences _xDissertations
650		0	_aUniversities and colleges _xDissertations
650		0	_aFinal Year Project
942			_2lcc _cTHESIS