The COVID-19 fake news detection in Thai social texts

Abstract

One important obstruction against Thai COVID-19 recovery is fake news shared on social media that is one of the “Artificial Intelligence Open Issues against COVID-19” reported by Montreal.AI. Misinformation spread is one of the main cyber-security threats that should be filtered out as the IDS for maintaining COVID-19 information quality. To detect fake news in Thai texts, Thai-NLP techniques are necessary. This paper proposes a state-of-the-art Thai COVID-19 fake news detection among word relations using transfer learning models. For pre-training from the global open COVID-19 datasets, the source dataset is constructed by English to Thai translating. The novel feature shifting is formulated to enlarge Thai text examples in target dataset. Machine translation can be used for constructing Thai source dataset to cope with the lack of local dataset for future Thai-NLP applications. To lead the knowledge in Thai text understanding forward, feature shifting is a promising accuracy improvement in fine-tuning stage.

Thai Fake News Detection Based on Information Retrieval, Natural Language Processing and Machine Learning

“…Aphiwongsophon and Chongstitvatana [10] focused only on Twitter data; there was no implementation for online detection. Mookdarsanit and Mookdarsanit [11] proposed a deep learning framework for Thai COVID-19 fake news detection from the social text. Mookdarsanit and Mookdarsanit [11] built transferred learning models including Bidirectional Encoder Representations from Transformers (BERT), Universal Language Model FIne-Tuning (ULMFIT), and Generative Pre-trained Transformer (GPT).…”

“…Mookdarsanit and Mookdarsanit [11] proposed a deep learning framework for Thai COVID-19 fake news detection from the social text. Mookdarsanit and Mookdarsanit [11] built transferred learning models including Bidirectional Encoder Representations from Transformers (BERT), Universal Language Model FIne-Tuning (ULMFIT), and Generative Pre-trained Transformer (GPT). The researchers used COVID-19 news open datasets translated to Thai and pretraining Thai COVID-19 deep learning models.…”

Sentiment analysis of Twitter posts related to the COVID-19 vaccines

“…For the more advanced analysis task, polarity detection can be used as a subtask to classify customers' reviews whether they like or dislike services [38], [39]. This helps in judging the quality of the products [2], [5], [40], [41].…”

“…Information obtained from social media may encourage individual to take vaccines or refuse them. The confidence of individuals in science and its role in solving this crisis can be destroyed by false information [4], which will affect the level of vaccination [5]- [7].…”

Visual Analytics of Twitter and Social Media Dataflows: a Casestudy of COVID-19 Rumors

“…They perform their analysis of the data on Sina Weibo, the most popular microblogging site in China. Last but not least papers solve the issue of analyzing misinformation to some extent [19,20,21], emphasizing methods of text analysis rather than visualization tools. Some recent studies describe machine learning approaches to investigation of rumor dissemination [22,23].…”