arXiv subjects

Sirinda Palahan

Publications and source records attributed to Sirinda Palahan.

3 recordsLinked to original sources

arXiv2025

Improving Access to Trade and Investment Information in Thailand through Intelligent Document Retrieval

Overseas investment and trade can be daunting for beginners due to the vast amount of complex information. This paper presents a chatbot system that integrates natural language processing and information retrieval techniques to simplify the document retrieval process. The proposed system identifies the most relevant content, enabling users to navigate the intricate landscape of foreign trade and investment more efficiently. Our methodology combines the BM25 model and a deep learning model to rank and retrieve documents, aiming to reduce noise in the document content and enhance the accuracy of the results. Experiments with Thai natural language queries have demonstrated the effectiveness of our system in retrieving pertinent documents. A user satisfaction survey further validated the system's effectiveness. Most respondents found the system helpful and agreed with the suggested documents, indicating its potential as a valuable tool for Thai entrepreneurs navigating foreign trade and investment.

cs.IR↗

arXiv2025

PythonPal: Enhancing Online Programming Education through Chatbot-Driven Personalized Feedback

The rise of online programming education has necessitated more effective, personalized interactions, a gap that PythonPal aims to fill through its innovative learning system integrated with a chatbot. This research delves into PythonPal's potential to enhance the online learning experience, especially in contexts with high student-to-teacher ratios where there is a need for personalized feedback. PythonPal's design, featuring modules for conversation, tutorials, and exercises, was evaluated through student interactions and feedback. Key findings reveal PythonPal's proficiency in syntax error recognition and user query comprehension, with its intent classification model showing high accuracy. The system's performance in error feedback, though varied, demonstrates both strengths and areas for enhancement. Student feedback indicated satisfactory query understanding and feedback accuracy but also pointed out the need for faster responses and improved interaction quality. PythonPal's deployment promises to significantly enhance online programming education by providing immediate, personalized feedback and interactive learning experiences, fostering a deeper understanding of programming concepts among students. These benefits mark a step forward in addressing the challenges of distance learning, making programming education more accessible and effective.

cs.HC↗

arXiv2025

Relationships between Students' Social Roles and Academic Performance based on Social Network Analysis

Peer interaction and social roles have been important factors in students' academic performance. Recent work on what influences academic performance in Thailand has focused on the quality of a school, students' backgrounds, and students themselves. A few works have analyzed the correlation between social roles and students' academic achievement. Therefore, this study was designed to measure the social networks of Thai undergraduate students and analyze the relationship between their roles in social networks and academic outcomes. The data analysis was based on social network theory and permutation test. Social network theory was used to measure essential network characteristics and extract social roles. Four roles were extracted in a social network: central members, clique members, liaisons, and isolators, and analyzed a relationship between the roles and academic performance. Data was collected via questionnaires from 384 students and used to build two types of networks: friend networks and study-helper networks. A permutation test was used for statistical hypothesis testing. The results showed that 1) Being a central member positively correlates with academic performance in friend and study-helper networks. The correlation coefficients between the degree of being a central member and academic performance are also positive in all schools and both types of networks. 2) Being an isolator negatively correlates with academic performance in study-helper networks. These results indicate that a social network plays a vital role in academic performance. The results suggest that academic institutes should encourage the development of students' social networks and strengthen the networks so that students can exchange their knowledge easier and help each other in learning, leading to better academic performance.

cs.SI↗