Sentimental Analysis and Keyword Extraction from Thai Users of Facebook in COVID-19 Period

Main Article Content

Boonthida Chiraratanasopha

Abstract

The new outbreak of Covid-19 leads to the confusion and has many effects on people including change in lifestyle and income opportunity. With the campaign of social distancing and stay-home, it becomes difficult to obtain people opinion using traditional methods such as questionnaire and interview. This work thus applies natural language processing tasks including keyword detection and sentimental analysis to analyze a trend of topics and their feelings towards the new outbreak of Covid-19 from Facebook posts. Detected keywords represent significant topics people were frequently mentioned while sentiment helps to reveal people feeling towards the topics. This study collected Facebook data related to Covid-19 posted between 1st November 2020 and 5th January, 2021 from those setting home location in Three Southern Border Provinces of Thailand for 3,127 posts. The keyword detection results indicate that there are four main groups of terms frequently discussed online as terms related disease prevention, terms about worry, terms about healthcare and treatment, and terms related to government policy. From results of sentimental analysis, the collected posts were separated to 80.07% negative posts, 14.42% positive posts and 15.45% neutral posts. Majority of the negative posts (46%) was about feeling frustrated of illegal activities causing the new outbreak whilst 56% of the positive posts were feeling impressive and praising towards fast attempt on prevention of Covid-19 spreading.

Article Details

How to Cite
1.
Chiraratanasopha B. Sentimental Analysis and Keyword Extraction from Thai Users of Facebook in COVID-19 Period. Prog Appl Sci Tech. [Internet]. 2021 Mar. 26 [cited 2024 Apr. 23];11(1):66-72. Available from: https://ph02.tci-thaijo.org/index.php/past/article/view/243241
Section
Information and Communications Technology

References

Rojratanavijit J, Eiamsithipan, C. Analysing Thai Social Media Content to Improve Customer Satisfaction. In The 25th International Conference on Electricity Distribution 2019 June 3-6. pp.1-5.

Katchapakirin K, Wongpatikaseree K, Yomaboot P, Kaewpitakkun Y. Facebook social media for depression detection in the Thai community. In2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE) 2018 Jul 11 (pp. 1-6). IEEE.

Liebeskind C, Nahon K, HaCohen-Kerner Y, Manor Y. Comparing Sentiment Analysis Models to Classify Attitudes of Political Comments on Facebook (November 2016). Polibits. Sci.. 2017;55:17-23.

Piyatumrong A, Sangkeettrakarn C, Haruechaiyasak C, Kongthon A. Finding Key Terms Representing Events from Thai Twitter. InInternational Symposium on Natural Language Processing 2016 Feb 10 (pp. 73-87). Springer, Cham.

Thanasopon B, Buranapanitkij J, Netisopakul P. Mining Social Media Crowd Trends from Thai Text Posts and Comments. Malays. J. Comput. Sci. 2019 Dec 23:96-108.

Dey L, Chakraborty S, Biswas A, Bose B, Tiwari S. Sentiment analysis of review datasets using naive bayes and k-nn classifier. arXiv preprint arXiv:1610.09982. 2016 Oct 31.

Chumwatana T. Comment Analysis for Product and Service Satisfaction from Thai Customers’ Review in Social Network. J. of Inform. and Commun. Technology. 2018 Mar 28;17(2):271-89.

Wang H, Wang Z, Dong Y, Chang R, Xu C, Yu X, Zhang S, Tsamlag L, Shang M, Huang J, Wang Y. Phase-adjusted estimation of the number of coronavirus disease 2019 cases in Wuhan, China. Cell Discov. 2020 Feb 24;6(1):1-8.

Minister of Public Health (MOPH). Thailand’s experience in the COVID-19 Response. (Accessed March 10, 2021, at https://ddc.moph. go.th/viralpneumonia/eng/file/pub_doc/LDoc9.pdf)

Bloomberg. (2020, March 25). Thailand to Impose Broad Lockdown to Fight Novel Coronavirus. (Accessed March 11, 2021, at https://www.bloomberg.com/news/articles/ 2020-03-25/thailand-to-impose-broad-lockdown-to-fight-spread-of-coronavirus)

Department of Disease Control (DDC). Guidelines for hotel business operators, service place, or resorts for tourists (Latest announcement on March 22, 2020) (Accessed March 14, 2021, at https://ddc.moph.go.th/ viralpneumonia/file/im_commands/im_com mands02.pdf) (In Thai)

Thaipbsworld. (2020, July 8). DCD says first wave of COVID-19 pandemic in Thailand has ended. (Accessed March 12, 2021, at https://www.thaipbsworld.com/dcd-says-first-wave-of-covid-19-pandemic-in-thailand-has-ended/)

Bangkokpost. (2020, Sep 5). Six caught sneaking in from Myanmar (Accessed March 13, 2021, at https://www.bangkokpost.com/ thailand/general/1980375)

Thong-iad K, Netisopakul P. Comparison of Thai Sentence Sentiment Tagging Methods Using Thai Sentiment Resource. In International Conference on Computing and Information Technology 2019 Jul 4 (pp. 89-98). Springer, Cham.

Srinilta C, Sunhem W, Tungjitnob S, Thasanthiah S, Vatathanavaro S. Lyric-based sentiment polarity classification of Thai songs. InProceedings of the International Multi Conference of Engineers and Computer Scientists 2017.

Nomponkrang T, Sanrach C. The Comparison of Algorithms for Thai-Sentence Classification. Int. J. Inf. Educ. Technol. 2016 Oct;6(10):801-808.

Chanlekha H, Damdoung W, Suktarachan M. The Development of Semi-automatic Sentiment Lexicon Construction Tool for Thai Sentiment Analysis. InInternational Symposium on Natural Language Processing 2016 Feb 10 (pp. 97-111). Springer, Cham.

Inrak P, Sinthupinyo S. Applying latent semantic analysis to classify emotions in Thai text. In2010 2nd International Conference on Computer Engineering and Technology 2010 Apr 16 (Vol. 6, pp. V6-450). IEEE.

Vateekul P, Koomsubha T. A study of sentiment analysis using deep learning techniques on Thai Twitter data. In2016 13th International Joint Conference on Computer Science and Software Engineering (JCSSE) 2016 Jul 13 (pp. 1-6). IEEE.

Songram P, Jareanpon C. Opinion Mining of Thai Politics on Facebook Status Updates. InProceedings of the 3rd IIAE International Conference on Intelligent Systems and Image Processing 2015 September 2-5. pp. 240-245.

Sarakit P, Theeramunkong T, Haruechaiyasak C, Okumura M. Classifying emotion in Thai youtube comments. In2015 6th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES) 2015 Mar 22 (pp. 1-5). IEEE.

LexTo-Thai Lexeme Tokenizer (LongLexto). [online] Source: http://www.sansarn.com/lexto/

APIs and Services Sentiment Analysis [online] Source: https://aiforthai.in.th/service_sa.php