Thai Sentiment Research Articles

An Efficient Deep Learning for Thai Sentiment Analysis

The number of reviews from customers on travel websites and platforms is quickly increasing. They provide people with the ability to write reviews about their experience with respect to service quality, location, room, and cleanliness, thereby helping others before booking hotels. Many people fail to consider hotel bookings because the numerous reviews take a long time to read, and many are in a non-native language. Thus, hotel businesses need an efficient process to analyze and categorize the polarity of reviews as positive, negative, or neutral. In particular, low-resource languages such as Thai have greater limitations in terms of resources to classify sentiment polarity. In this paper, a sentiment analysis method is proposed for Thai sentiment classification in the hotel domain. Firstly, the Word2Vec technique (the continuous bag-of-words (CBOW) and skip-gram approaches) was applied to create word embeddings of different vector dimensions. Secondly, each word embedding model was combined with deep learning (DL) models to observe the impact of each word vector dimension result. We compared the performance of nine DL models (CNN, LSTM, Bi-LSTM, GRU, Bi-GRU, CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU) with different numbers of layers to evaluate their performance in polarity classification. The dataset was classified using the FastText and BERT pre-trained models to carry out the sentiment polarity classification. Finally, our experimental results show that the WangchanBERTa model slightly improved the accuracy, producing a value of 0.9225, and the skip-gram and CNN model combination outperformed other DL models, reaching an accuracy of 0.9170. From the experiments, we found that the word vector dimensions, hyperparameter values, and the number of layers of the DL models affected the performance of sentiment classification. Our research provides guidance for setting suitable hyperparameter values to improve the accuracy of sentiment classification for the Thai language in the hotel domain.

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

SETAR: Stacking Ensemble Learning for Thai Sentiment Analysis Using RoBERTa and Hybrid Feature Representation

Setar: A Novel Method of Stacking Ensemble Learning for Thai Sentiment Analysis Using Roberta and Hybrid Feature Representation

Setar: A Novel Method of Stacking Ensemble Learning for Thai Sentiment Analysis Using Roberta and Hybrid Feature Representation

Thai sentiment analysis with deep learning techniques: A comparative study based on word embedding, POS-tag, and sentic features

A smart city connects physical, information technology, social, and business infrastructures together to leverage their collective intelligence. Feedback drives improvements in service, city development, and quality of life in the city. Therefore, sentiment analysis in real-time of opinions expressed in text form by residents in the city is absolutely necessary. Nowadays, machine learning is widely applied to sentiment analysis of decisions in business, especially deep learning. In this experiment, we evaluated and compared the performances of several conventional deep learning models: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Bidirectional LSTM (Bi-LSTM), in sentiment analysis of Thai children tales. In several previous studies, many features have been used in all of the models mentioned, features such as word embedding that helps a model to understand the semantics of each word, POS-tag that helps a model to understand the grammatical function of words, and sentic that helps a model to understand the emotion of words. Some combinations of these features have also been used. The results of this experiment show that the CNN model that used all three features gave the best result of 0.817 F1-score at p < 0.01, which was significantly better than all other models.

Hypothesis testing based on observation from Thai sentiment classification

This work focuses on error analyzes from the Support Vector Machine (SVM) classification on Thai children stories at a sentence level. The construction of the Sentiment Term Tagging System (STTS) program allows the researchers to make observations and hypothesize around the areas where most anomalies occur. Three hypotheses, based on terms sentiment chosen for SVM predictions, are evidently proved to hold. In addition, a number of ways to improve the Thai sentiment classification research are suggested, including considerations to add negation into the process, add weighing scheme for different part-of-speech, disambiguate word senses, and update the Thai sentiment resource.

Sentiment analysis of Thai children stories

Sentiment Text Tagging System (STTS) with Thai sentiment resource has been developed and used to tag emotions directly to words and sentences in Thai children stories. The Thai sentiment resource, developed from SenticNet2 resource, groups emotions into four independent but concomitant dimensions: pleasantness, attention, sensitivity and aptitude. The measure of each dimension is called a sentic value of that dimension. Thai sentiment resource stores each word's sentic value and polarity value, a value calculated from the sentic value, in the form of floating point number. The resource was constructed from bi-directional translation of 14,244 English terms in SenticNet2 into 16,584 Thai terms. The main purpose of this study was to implement a sentiment analysis of Thai children stories system with support vector machine using a set of proposed discriminating features for classifying emotions. It was found that the system can achieve 75.67 % of accuracy.

Thai Society During World War II

Because she was not a Western colonial country, but an Asian Kingdom and a member of the Axis Power, wartime Thailand was free from Japanese military administration and a able to keep aloof from warfare after the friendly entry of the Japanese army, Thai political leaders assumed a pattern of “compromise” rather than “hostility” in response to the Japanese impact. Although intellectually, most Thai leaders did not agree with the Japanese idea of “The Great East Asia Go-prosperity Sphere, ” they accelerated an allied relationship with Japan to avoid a possibly critical situation of Japanese militarism sweeping all over the country. For her own national benefit in facing increasing Japanese power in Southeast Asia, Thailand put pressure on the anti-Japanese boycott movement of the Chinese within a country, sat on her fence of neutrality and tried to remain out side the Japanese military occupation until the opening day of the war. Even after December 8, 1941, when she recognized the friendly entry of the Japanese army, Thailand tried hard to stand behind the bay line by contributing economic ally to the Japanese military operation in Burma, Malaya and Singapore.In wartime, Pibul Songkram, Prime Minister of the Government, promoted Rathaniyom (Patriotic Movement) and Thai Yai (Great Thai Nation Movement through which he wanted to keep national stability based on of traditional Thai sentiment rather than the idea of individual freedom from the Constitutional Revolution in 1932. In terms of motivation, therefore, these movements were quite different from the Japanese idea of the “Co-prosperity Sphere.” Meanwhile, the dynamics of the anti-Japanese “Free Thai” movement were accelerated by Thai elites and university students then in the United States and the United Kingdom. There they carried out the actual plan to develop their resistance against Japan. On the other hand, Thai leaders, except several domestic “Free Thai” leaders, outwardly continued their friendly relations with the Japanese while secretly linking up with the “Free Thai” members in order to find a new place for themselves after the war. With the benefits of this duality, they reserved their own clear cut opinion and left rooms for changing attitudes to their advantage.Chinese leaders in economic circles also had similar patterns of response. Although they started the anti-Japanese National Salvation Movement in 1937, which was motivated from loyalty to their native land, they joined neither the all Chinese united front in Southeast Asia nor the overseas Chinese good-will tour party to Chungking and Yennan in 1938. However, from 1938 the Chinese in Thailand began cooperating with the national policy of the Thai government and, after war erupted, made contributions by procuring for the Japanese army. In reply to a requisition for labour for army railway construction between Burma and Thailand in 1943, the Chinese again tried to keep their security in the country by means of economic cooperation in offering munitions war, rather than by sending labour power for dreadful construction. In the meantime, however, they donated funds secretly to members of the “Free Thai” movement. Chang Lan-ch'en, former President of the Chinese Chamber of Commerce in Thailand, was a leader of pro-Japanse group during the war, but was able to return to the some position again in 1948 and held thee post until 1961 when he died. Pibul was also reinstalled in his former position in 1948 and was Prime Minister until 1957. These two political and economic leaders began to leave room for changing attitudes by the end of the war, to enhance their reinstatement in the post-war period.