Improving Thai Sentiment Analysis Accuracy with Emoji Classification by Deep Learning and Stacking Models: A Case Study of Hotel Reviews

Walaithip Bunyatisai; Suwika Plubin; Knavoot Jiamwattanapong; Bandhita Plubin

doi:10.57239/PJLSS-2025-23.1.007

Author(s)

Walaithip Bunyatisai Department of statistics, Faculty of science, Chiang Mai University, Chiang Mai, Thailand

Suwika Plubin Department of statistics, Faculty of science, Chiang Mai University, Chiang Mai, Thailand

Knavoot Jiamwattanapong Faculty of Liberal Arts, Rajamangala University of Technology Rattanakosin,Nakhon Pathom, Thailand

Bandhita Plubin ,Department of statistics, Faculty of science, Chiang Mai University, Chiang Mai, Thailand

Abstract

Sentiment analysis presents unique challenges in hotel reviews, particularly in languages like Thai, renowned for nuanced expressions. Understanding customer opinions is pivotal, especially in domains such as hotel reviews, where subjective expressions prevail. This study delves into methodologies to refine sentiment analysis accuracy in Thai hotel reviews by integrating emoji classification with Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and stacking models. Through comparing models with and without emoji inclusion, we meticulously evaluate their performance metrics encompassing accuracy, precision, recall, and F1-score. The pinnacle achievement of 92.4% accuracy underscores the efficacy of advanced stacking techniques complemented by emoji integration. Our findings underscore the superiority of models encompassing emojis, affirming the value of amalgamating textual and emoji data. Leveraging sophisticated deep learning techniques and stacking models, our approach adeptly captures the subtle nuances of sentiment expressed in Thai text, resulting in heightened accuracy in sentiment analysis. This research underscores the paramount importance of embracing diverse data sources and sophisticated modeling strategies to elevate sentiment analysis accuracy in Thai hotel reviews.

Publication Details

Page(s) 65-77

DOI 10.57239/PJLSS-2025-23.1.007

Published Journal: Pakistan Journal of Life and Social Sciences, Volume: 23, Issue: 1, Year: 2025

Request the full text from PASTIC

Keywords

Sentiment Analysis Emoji Classification Emoji Emotion Convolutional Neural Networks Recurrent Neural Networks

References

Alharbi NM,Alghamdi NS,Amri EH,JF EH .2021 .Evaluation of sentiment analysis via word embedding and RNN variants for Amazon online reviews. Math Probl Eng:, : 1-10.

Alshenqeeti H .2016 .Are emojis creating a new or old visual language for new generations? a sociosemiotic study. Advances in Language and Literary Studies, 7(6) : 56-69.

Boutet I,LeBlanc M,Chamberland JA,Collin CA .2021 .Emoji infuence emotional communication, social attributions, and information processing. Comput Human Behav, : .

Chen Y,Xiong J,Xu W,Zuo J .2019 .A novel online incremental and decremental learning algorithm based on variable support vector machine. Cluster Comput, 22(S3) : 7435-7445.

Dehler-Holland J,Okoh M,Keles D .2021 .Assessing technology legitimacy with topic models and sentiment analysis - The case of wind power in Germany. Technol Forecast Soc Change, 121354 : 121354.

Demirci GM,Keskin SR,Dogan G . .- December) Sentiment Analysis in Turkish with Deep Learning. In Proceedings of the IEEE International Conference on Big Data (Big Data), : 2215-2221.

Dey P,Dey S .2023 .Sentiment Analysis of Text and Emoji Data for Twitter Network. Journal for Engineering and Pure Sciences, 3 : 1e10.

Erle TM.,Schmid K,Goslar SH,Martin JD .2022 .Emojis as social information in digital communication. Emotion, 22(7) : 1529-1543.

Felbo B,Mislove A,Søgaard A,Rahwan I,Lehmann S .2017 .Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, : 1615-1625.

Ganster T,Eimler SC,Krämer NC .2011 .Same same but different!? The differential influence of smilies and emoticons on person perception. Cyberpsychol Behav Soc Netw, 0179(4) : 226-230.

Haruechaiyasak C,Kongthon A .2013 .October) LexToPlus: A Thai Lexeme Tokenization and Normalization Tool. In Proceedings of the Sixth International Conference on Information, Communications & Signal Processing, : .

Hirata E,Matsuda T .2023 .Examining logistics developments in post-pandemic Japan through sentiment analysis of twitter data. Asian transpo stud 9, 100110 : 10.

Hochreiter S,Schmidhuber J .1997 .Long Short-Term Memory. Neural Comput, 9(8) : 1735-1780.

Hu T,Guo H,Sun H,Nguyen T,Luo J .2017 .Spice up your chat: The intentions and sentiment efects of using emojis. In Proceedings of Eleventh International AAAI Conference on Web and Social Media, 11(1) : 14869-111.

Khamphakdee N,Seresangtakul P .2021 .Sentiment Analysis for Thai Language in Hotel Domain Using Machine Learning Algorithms. Acta Inform Prag, 10(2) : 155-171.

Kim H,Jeong YS .2019 .Sentiment Classification Using Convolutional Neural Networks. Appl Sci, 9(11) : 2347.

Manalu BU,Efendi S (2020- September BU . .Deep Learning Performance in Sentiment Analysis. In Proceedings of the 4rd International Conference on Electrical, Telecommunication and Computer, : .

Mintel .2013 .Holiday planning and booking process - UK. Mintel Report, : .

Mohammed A,Himmi M,Bellafkih M,Talaghzi J,Bennane A .2023 .Sentiment analysis in digital learning: Comparing Lexical, Traditional machine learning. and deep learning approaches. 1- 6. 10.1109/SITA60746, : .

KK Mohbey . .Sentiment analysis for product rating using a deep learning approach. (2021-March). In Proceedings of the International Conference on Artificial Intelligence and Smart Systems (ICAIS), : 121-126.

Mukherjee S,Bhattacharyya P .2012 .eds) Computational Linguistics and Intelligent Text Processing. CICLing 2012. Lect Notes Comput Sc 7181, : 39.

Neel LAG,McKechnie JG,Robus CM,Hand CJ .2023 .Emoji Alter the Perception of Emotion in Affectively Neutral Text messages. J Nonverbal Behav, 47 : 83-97.

Poncelas A,Pidchamook W,Hadley J,Way A .2004 .Multiple Segmentations of Thai Sentences for Neural Machine Translation. Marseille. arXiv, : 240-244.

Razali NAM,Malizan NA,Hasbullah NA,Wook M,Zainuddin NM,Ishak KK,Ramli S,Sukardi S .2021 .Opinion mining for national security: Techniques, domain applications, challenges and research opportunities. J Big Data, 10(1) : PMC8642766.

Saadah MN,Atmagi RW,Rahayu DS,Arifin AZ .2013 .Information Retrieval of Text. , : .

Salur MU,Aydin I .2020 .A novel hybrid deep learning model for sentiment classification. In: IEEE Access, 2982538 : 58080-58093.

Singkul S,Khampingyot B,Maharattamalai N,Taerungruang S,Tawunrat C .2019 .Parsing Thai Social Data: A New Challenge for Thai NLP. , 9045639 : NLP48611.

Shiha MO,Ayvaz S .2017 .The Effects of Emoji in Sentiment Analysis. Int J of Comput Electr Eng, 9(1) : 360-369.

Singla C,Al-Wesabi N,Singh Pathania Y,Sulaiman Alfurhood B,Mustafa Hilal A,Rizwanullah M,Ahmed Hamza M,Mahzari M .2022 .An optimized deep learning model for emotion classification in tweets. Comput Mater Contin, 020480(3) : 6365-6380.

Ting KM,Witten IH .1999 .Issues in stacked generalization. J Artif Intell Res, 10 : 271-289.

Wolpert DH .1992 .Stacked Generalization. Neural Networks, 5(2) : 241-259.

Xiang S (2021-November ,Education (ICISE-IE ) . .Deep Learning Framework Study for Twitter Sentiment Analysis. In Proceedings of the 2nd International Conference on Information Science, : 517-520.

Yang L,Wang J,Tang Z,NN Z .2019 .Using conditional random fields to optimize a self-adaptive Bell-LaPadula model in control systems. IEEE Trans Syst Man Cybern Syst, 2937551(7) : 4505-4519.

Zeng D,Dai Y,Li F,Sherratt R.,Wang J .2018 .Adversarial learning for distant supervised relation extraction. Comput Mater Contin, 055(1) : 121-136.

Zhang L,Wang S,Liu B .2018 .Deep learning for sentiment analysis: A survey. Wiley Interdiscipl. Rev., Data Mining Knowl. Discovery, 8(4) : e1253.

Zhou J,Lu Y,Dai HN,Wang H,Xiao H .2018 .Sentiment Analysis of Chinese Microblog Based on Stacked Bidirectional LSTM. , 00034 : 10-167.