KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 7 of 7

Some of the metrics are blocked by your
consent settings
Detecting Cyberbullying in Thai Memes: A Multimodal Approach Using Deep Learning
(2025-01-01)
Phosit, Salisa
;
Kongsamlit, Sawarod
;
Pasupa, Kitsuchart
Today, people tend to communicate more through the Internet due to its speed and convenience. However, there are hidden drawbacks, such as the misuse of online social media and the occurrence of cyberbullying, which can lead to negative feelings or even mental health issues. Therefore, it is necessary to develop cyberbullying detection methods. While these methods have been studied in various languages, more research is still needed in Thai due to its status as a low-resource language. This research aims to develop a model for detecting cyberbullying in online social media, specifically focusing on memes. The primary objective is to develop a Thai meme dataset collected from Facebook using deep learning techniques for model development. The developed model utilizes multimodal concepts, incorporating both text and images. In addition to detecting cyberbullying, it also considers other aspects, such as harmfulness, offensiveness, sarcasm, sentiment, emotions, and topics. Our findings indicate that multimodal models outperform unimodal models, with the combination of WangchanBERTa and ViT-B/32 achieving the highest performance across most tasks. Compared to the best-performing unimodal models, the multimodal approach resulted in a 1.53% improvement in the F<inf>1</inf> -Score on the Bully task. This underscores the significant value of integrating textual and visual information for a more robust and nuanced understanding of cyberbullying content.
Some of the metrics are blocked by your
consent settings
HANCaps: A Two-Channel Deep Learning Framework for Fake News Detection in Thai
(2024-01-01)
Maity, Krishanu
;
Bhattacharya, Shaubhik
;
Phosit, Salisa
;
Kongsamlit, Sawarod
;
Saha, Sriparna
The rapid advancement of internet technology, widespread smartphone usage, and the rise of social media platforms have drastically transformed the global communication landscape. These developments have resulted in both positive and negative consequences. On the one hand, they have facilitated the dissemination of information, connecting individuals across vast distances and fostering diverse perspectives. On the other hand, the ease of access to online platforms has led to the proliferation of misinformation, often in the form of fake news. Detecting and combatting fake news has become crucial to mitigate its adverse effects on society. This paper presents an investigation into fake news detection in the Thai language. It addresses current limitations in this domain by proposing a novel two-channel deep learning model named HANCaps, which integrates BERT and FastText embeddings with a hierarchical attention network and capsule network. The HANCaps model utilizes the BERT language model as one channel input, while the other channel incorporates pre-trained FastText embeddings. The proposed model undergoes evaluation using a benchmark Thai fake news dataset, and extensive experimentation demonstrates that HANCaps outperforms state-of-the-art methods by up to 3.28% in terms of F1 score, showcasing its superior performance.
Some of the metrics are blocked by your
consent settings
Characterization of the Gut Microbiota in Urban Thai Individuals Reveals Enterotype-Specific Signature
(2023-01-01)
Sinsuebchuea, Jiramaetha
;
Paenkaew, Prasobsook
;
Wutthiin, Montree
;
Nantanaranon, Thatchawanon
;
Laeman, Kiattiyot
Gut microbiota play vital roles in human health, utilizing indigestible nutrients, producing essential substances, regulating the immune system, and inhibiting pathogen growth. Gut microbial profiles are dependent on populations, geographical locations, and long-term dietary patterns resulting in individual uniqueness. Gut microbiota can be classified into enterotypes based on their patterns. Understanding gut enterotype enables us to interpret the capability in macronutrient digestion, essential substance production, and microbial co-occurrence. However, there is still no detailed characterization of gut microbiota enterotype in urban Thai people. In this study, we characterized the gut microbiota of urban Thai individuals by amplicon sequencing and classified their profiles into enterotypes, including Prevotella (EnP) and Bacteroides (EnB) enterotypes. Enterotypes were associated with lifestyle, dietary habits, bacterial diversity, differential taxa, and microbial pathways. Microbe–microbe interactions have been studied via co-occurrence networks. EnP had lower α-diversities than those in EnB. A correlation analysis revealed that the Prevotella genus, the predominant taxa of EnP, has a negative correlation with α-diversities. Microbial function enrichment analysis revealed that the biosynthesis pathways of B vitamins and fatty acids were significantly enriched in EnP and EnB, respectively. Interestingly, Ruminococcaceae, resistant starch degraders, were the hubs of both enterotypes, and strongly correlated with microbial diversity, suggesting that traditional Thai food, consisting of rice and vegetables, might be the important drivers contributing to the gut microbiota uniqueness in urban Thai individuals. Overall findings revealed the biological uniqueness of gut enterotype in urban Thai people, which will be advantageous for developing gut microbiome-based diagnostic tools.
Some of the metrics are blocked by your
consent settings
FastThaiCaps: A Transformer Based Capsule Network for Hate Speech Detection in Thai Language
(2023-01-01)
Maity, Krishanu
;
Bhattacharya, Shaubhik
;
Saha, Sriparna
;
Janoai, Suwika
;
Pasupa, Kitsuchart
The advent of technology has led to people sharing their views openly like never before. Parallelly, cyberbullying and hate speech content have also increased as a side effect that is potentially hazardous to society. While plenty of research is going on to detect online hate speech in English, there is very little research on the Thai language. To investigate how noisy Thai posts can be handled effectively, in this work, we have developed a two-channel deep learning model FastThaiCaps based on BERT and FastText embedding along with a capsule network. The input to one channel is the BERT language model, and that to the other is the pre-trained FastText embedding. Our model has been evaluated on a benchmark Thai dataset categorized into four categories, i.e., peace speech, neutral speech, level-1 hate speech, and level-2 hate speech. Experiments show that FastThaiCaps outperforms state-of-the-art methods by up to 3.11% in terms F1 score.
Some of the metrics are blocked by your
consent settings
Ex-ThaiHate: A Generative Multi-task Framework for Sentiment and Emotion Aware Hate Speech Detection with Explanation in Thai
(2023-01-01)
Maity, Krishanu
;
Bhattacharya, Shaubhik
;
Phosit, Salisa
;
Kongsamlit, Sawarod
;
Saha, Sriparna
Social media platforms have both positive and negative impacts on users in diverse societies. One of the adverse effects of social media platforms is the usage of hate and offensive language, which not only fosters prejudice but also harms the vulnerable. Additionally, a person’s sentiment and emotional state heavily influence the intended content of any social media post. Despite extensive research being conducted to detect online hate speech in English, there is a lack of similar studies on low-resource languages such as Thai. The recent enactment of laws like the “right to explanations” in the General Data Protection Regulation has stimulated the development of interpretable models rather than solely focusing on performance. Motivated by this, we created the first benchmark hate speech corpus, called Ex-ThaiHate, in the Thai language. Each post is annotated with four labels, namely hate, sentiment, emotion, and rationales (explainability), which specify the phrases that are responsible for annotating the post as hate. In order to investigate the effect of sentiment and emotional information on detecting hate speech posts, we propose a unified generative framework called GenX, which redefines this multi-task problem as a text-to-text generation task to simultaneously solve four tasks: hate-speech identification, rationale detection, sentiment, and emotion detection. Our extensive experiments demonstrate that GenX significantly outperforms all baselines and state-of-the-art models, thereby highlighting its effectiveness in detecting hate speech and identifying the rationales in low-resource languages. The code and dataset are available at https://github.com/dsmlr/Ex-ThaiHate. Disclaimer: The article contains offensive text and profanity. This is due to the nature of the work and does not reflect any opinion or stance of the authors.
Some of the metrics are blocked by your
consent settings
Thai home improvement retailer customer loyalty: A SEM analysis
(2018-01-01)
Suebsaiaun, Atisin
;
Pimolsathean, Thepparat
The contest between ‘bricks versus clicks’, with the disruptive effect of e-commerce on traditional retail formats, is starting to be felt in Thailand. Specifically, home improvement retailers are therefore having to adapt, by creating unique online shopping experiences, which is enhanced by sophisticated electronic customer relationship management (eCRM) systems designed to capture and retain a digitally savvy Thai consumer. Seeing the critical nature if the eCRM process, the researchers undertook an analysis of the opinions of 465 consumers who shopped at one of the five top Thai home improvement retailer stores. Using LISREL 9.10 software to examine the nine hypotheses structural equation model (SEM), it was determined that all the causal factors in the model have a positive influence on customer loyalty, which can be explained by 73% of the variance in Thai home improvement retailer customer loyalty (R<sup>2</sup>). The causal variables influencing customer loyalty ranked from highest to lowest, were SERVQUAL, customer satisfaction, corporate social responsibility, and eCRM, with a total value of the influence at 0.57, 0.38, 0.29 and 0.29, respectively. Additionally, the study revealed that extreme caution was needed when social media platforms are used in marketing, as overwhelming consumers with poorly targeted, ‘spray and pray’ style marketing campaigns can generate disenfranchised consumers who unsubscribe from the marketer’s channel.
Some of the metrics are blocked by your
consent settings
Impact of cross-border migration on disease epidemics: Case of the P. falciparum and P. vivax malaria epidemic along the Thai-Myanmar border
(2010-03-01)
Pongsumpun, Puntani
;
Tang, I. Ming
The transmission of Plasmodium falciparum and Plasmodium vivax malaria in a mixed population of Thais and migrant Burmese living along the Thai-Myanmar border is studied through a mathematical model. The population is separated into two groups: Thai and Burmese. Each population in turn is divided into susceptible, infected, recovered and in case of vivax infection, a dormant subclass. The model is then modified to allow for some of the Burmese (given as a fraction P) to be infectious when they enter into Thailand. The behaviour of the modified model is obtained using a standard dynamical analysis. A new basic reproduction number is obtained. Numerical simulations of the modified model show that when P ≠ 0 and the same set of parameter values used in the initial model are used, the Thai population will be in the epidemic state. In other words, the repeated introduction of infectious Burmese (no matter how small of a number) will result in a malaria epidemic among the Thais irregardless of the public health practice undertaken by the Thai government. In the presence of the infected Burmese, the Thai government would have to increase the facilitites to treat the people who are infected by the malaria. © 2010 World Scientific Publishing Company.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results