NHNien-Lin Hsueh

Nien-Lin Hsueh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Nien-Lin Hsueh has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Help-Seeking in LLM-Assisted Learning: Behavioral Pathways and Their Limited Association with Subsequent Coding Process Efficiency

    by Lien-Chi Lai, Nien-Lin Hsueh

    Large language models (LLMs) are increasingly used in programming education to provide on-demand conceptual clarification, yet how students actually use this feature in mastery learning systems (in which learners must demonstrate conceptual competence before progressing)—and whether clarification interactions relate to subsequent learning—has received limited empirical study. This paper analyzes 732 student remediation episodes (366 students, 43 assignments) to examine how students move through the remediation branch of an LLM-assisted programming course, whether their behavioral pathway choices are associated with subsequent coding challenge efficiency, and what theoretical role the clarification function plays. The results show that 78.0% of remediation episodes follow a pure retesting strategy, with only 22.0% involving any clarification interaction. Clarification is highly concentrated on conceptual questions (84.7%) and occurs mostly in the first remediation round (86.3%). An effect size analysis reveals a large difference in remediation rounds between single immediate and single delayed clarifiers (Cliff’s δ=−0.912), suggesting that the timing of clarification is more strongly associated with remediation efficiency than its occurrence alone. mixed-effect linear models show no significant pathway effects on coding challenge process efficiency (active time and number of code snapshots; all p>0.05), a null result that is further examined through code-variability subgroup analyses. We argue that the clarification feature acts as a selective process-support mechanism: its observable value appears to lie in a shorter remediation process rather than in improved subsequent task efficiency, and this association is clearest when clarification occurs early. The findings have practical implications for the design of clarification features in AI-assisted learning systems and for instructional intervention strategies.


  • Open Access

    Design of a RAG-Based Customer Service Chatbot Enhanced with Knowledge Graph and GPT Evaluation: A Case Study in the Import Trade Industry

    by Nien-Lin Hsueh, Wei-Che Lin

    Amid the wave of digital transformation and customer service automation, traditional chatbots are increasingly challenged by their inability to handle unstructured data and complex queries. This issue is particularly critical in the import trade industry, where customer service representatives must respond promptly to diverse inquiries involving quality anomalies, order tracking, and product substitution. Existing rule-based or keyword-driven chatbots often fail to provide accurate responses, resulting in reduced customer satisfaction and increased operational burdens. This study proposes and implements a “Retrieval-Augmented Generation (RAG)-based Customer Service Chatbot,” integrating the RAG framework with a Neo4j-based knowledge graph, specifically tailored for the import trade domain. The system constructs a dedicated QA dataset, knowledge graph, and dynamic learning mechanism. It semantically vectorizes internal documents, meeting records, quality assurance procedures, and historical dialogues, establishing interrelated knowledge nodes to enhance the chatbot’s comprehension and response accuracy. The study also incorporates GPT-based response evaluation and a high-score caching strategy, enabling dynamic learning and knowledge enhancement. Experiments were conducted using 101 representative enterprise-level queries across six categories, reflecting real-world operational scenarios and inquiry needs. The results demonstrate that the combination of knowledge graphs and RAG technology effectively reduces AI hallucinations and improves response coverage and accuracy, thereby addressing complex problems in customer service applications. This paper not only presents a feasible AI implementation model for the import trading industry but also offers a practical architectural reference for domain-specific knowledge management in the import trade and allied sectors.


  • Open Access

    Development and Evaluation of Learning Portfolio Query System Based on LangChain Framework

    by Nien-Lin Hsueh, Wei-Ting Wang

    With the increasing popularity of online education platforms, the use frequency of students and teachers has gradually increased. A large volume of data is generated and analyzed daily on these platforms including course information and student learning status. However, traditional analysis methods often require substantial manpower and expertise. Large language models Chat GPT-4 offer a potential solution to this problem. This study aims to address this challenge by utilizing the large-scale language model framework LangChain and the database of the OpenEdu online education platform. We designed an interface capable of querying educational data in natural language. When a user queries in natural language, the large language model generates structured query language to query the database and converts the query back into natural language to respond to the user’s question. Two different query methods were developed based on LangChain components: the sequential query version and the Agent query version. Based on these methods, four different versions of prompt and model combinations were created. The accuracy in converting natural language to SQL was estimated, and error type analysis was conducted to enhance the system’s performance and accuracy. The execution accuracy reached up to 85.7%, with the primary error type in natural language-generated SQL being Schema Linking. By integrating large-scale language models into conversational query systems, a promising approach was developed for handling large-scale data queries on educational platforms.


  • Open Access

    Applying Large Language Model to User Experience Testing

    by Nien-Lin Hsueh, Hsuen-Jen Lin, Lien-Chi Lai

    The maturation of internet usage environments has elevated User Experience (UX) to a critical factor in system success. However, traditional manual UX testing methods are hampered by subjectivity and lack of standardization, resulting in time-consuming and costly processes. This study explores the potential of Large Language Models (LLMs) to address these challenges by developing an automated UX testing tool. Our innovative approach integrates the Rapi web recording tool to capture user interaction data with the analytical capabilities of LLMs, utilizing Nielsen’s usability heuristics as evaluation criteria. This methodology aims to significantly reduce the initial costs associated with UX testing while maintaining assessment quality. To validate the tool’s efficacy, we conducted a case study featuring a tennis-themed course reservation system. The system incorporated multiple scenarios per page, allowing users to perform tasks based on predefined goals. We employed our automated UX testing tool to evaluate screenshots and interaction logs from user sessions. Concurrently, we invited participants to test the system and complete UX questionnaires based on their experiences. Comparative analysis revealed that varying prompts in the automated UX testing tool yielded different outcomes, particularly in detecting interface elements. Notably, our tool demonstrated superior capability in identifying issues aligned with Nielsen’s usability principles compared to participant evaluations. This research contributes to the field of UX evaluation by leveraging advanced language models and established usability heuristics. Our findings suggest that LLM-based automated UX testing tools can offer more consistent and comprehensive assessments.


  • Open Access

    Design of an Online Programming Platform and a Study on Learners’ Testing Ability

    by Nien-Lin Hsueh, Lien-Chi Lai, Wei-Hsiang Tseng

    Online judge (OJ) systems are essential in programming education as they efficiently evaluate learners’ programming skills and reduce instructor workload. However, these systems often overlook the importance of software-testing concepts. To address this gap, we developed a system called Pytutor that integrates software-testing concepts to assess learners’ programming abilities and proficiency by exploring students’ test cases and learning behaviors. Drawing on software engineering theory and practical techniques, test capabilities are evaluated by analyzing the code coverage and mutation testing of Defining Test Cases. Since our experiment is conducted in an online environment, we can collect students’ learning behaviors and further analyze the relationship between software engineering abilities and learning behaviors. We also analyzed the differences in programming and testing abilities between computer science majors and non-computer-science majors. Our findings suggest that better testing abilities may contribute to the improvement in programming abilities, whereas in the current Taiwanese education context, computer science majors do not necessarily have better testing abilities. This result provides suggestions for us to strengthen software-testing education no matter which type of students it is targeted at.


  • Open Access

    Design and Implementation of Gamified Learning System for Mutation Testing

    by Nien-Lin Hsueh, Zeng Hung Xuan, Bilegjargal Daramsenge

    Mutation Testing is used to test case improvement mechanism for evaluating the effectiveness of test cases by generating a large number of mutants. In the past, some approaches are proposed to improve the performance of generating the mutants. In recent years, many studies have begun to explore the software engineering education of mutation testing, trying to make students understand its concept through gamification. In this paper, we apply gamification theory and build a gamified learning system for mutation testing, named code immunity boost (CIB), taking the story of vaccine development as a sense of mission. We invited students to learn mutation testing through the relationship between leukocyte (test case), vaccine (mutant) and human body (program). Students can play the role of a vaccine and stimulate the testing of test cases by writing mutants to improve the quality of the program. We adopted the benchmark programs commonly used in mutation testing research, and developed a code vaccine incubator (CVI) tool to generate a large number of mutants as the experimental cornerstone of this study. Final experiments show that our tool can help mutation testing education, as the performance and quality of the experimental group is better than that of the control group. The response from the questionnaire also shows students like learning by our gamified tool. We therefore recommend to promote such software testing education approach by integrating our tool with popular online programming tools such as Online Judge system.


  • Open Access

    An Alliance-Based Term Project in Software Quality Courses: a Lesson Learned

    by Nien-Lin Hsueh

    Software testing education has become important in the field of software engineering education. In the previous software quality assurance course, students were asked to form teams to complete a term project. By working on term projects, students can learn programming skills and test skills in a practical way. However, from the experience of the last 3 years, we found that students only did unit testing and system performance testing well but did poorly in integration testing. In addition, students do not yet have the concept of system decomposition and integration, even though it is important during software development. In this paper we report our improvements to software testing course design - an alliance-based approach. In the term project, students are organized into teams and many teams are grouped into alliances. Each alliance has a team of masters building game platforms for others. The master team must define the application interface to interact with other gaming teams, and they must perform integration tests based on the defined interface. In this paper we report our experiences and student feedback on the educational approach.


  • A test case refactoring approach for pattern-based software development

    by Peng-Hua Chu, Nien-Lin Hsueh, Hong-Hsiang Chen, Chien-Hung Liu


  • Reversible Data Hiding Based on Three-Circular-Pixel Difference Expansion

    by Ching-Chiuan Lin, Shun-Ping Yang, Nien-Lin Hsueh

    This paper proposes a reversible data hiding scheme based on three-circular-pixel (TCP) difference expansion. To embed a message in an image, the image is divided into three-pixel blocks, each of which is, then, transformed into a TCP block with two differences. When the pixel value of the largest pixel in the TCP block is increased, two differences are increased – one is between the largest and the smallest, and the other is between the largest and the middle. Expanding the two differences in the block by increasing the largest pixel value may make the image less modified. In addition, the number of pixel pairs is increased to two thirds of the number of pixels in the image. Compared to Tian's study, both the visual quality and the embedding capacity of the image are significantly improved.