Journal of Information Technology and Innovation

Library Administrators in the Era of Artificial Intelligence : Rethinking Managerial Mindsets and Practices

Panida Kaewkoon — 2025-12-29

Libraries constitute essential institutions for the provision of information, knowledge, and resources. In order to respond effectively to rapidly changing user demands, they must adapt to the emergence of artificial intelligence (AI) technologies. This transformation necessarily begins with library administrators, who are required to assume leadership roles suited to the AI era. Such leadership entails a shift from using technology solely as a means of operational efficiency toward employing AI as a strategic driver of organizational development and culture, informed by in-depth data analysis and trend forecasting, while maintaining a human-centered orientation and adherence to ethical principles.

Within this context, the traditional 4M management framework can be recalibrated as follows: (1) personnel management based on role assignments rather than fixed positions; (2) the reconfiguration of budget control into strategic investment; (3) the deployment of AI in resource management; and (4) the transformation of administrative processes into a learning ecosystem subject to ongoing monitoring and evaluation.

Furthermore, library administrators should critically review existing processes to identify and implement pilot projects that integrate AI with current technologies prior to organization-wide adoption. Simultaneously, they should reassess organizational structures and redefine staff roles in order to move beyond linear personnel management. Establishing an organizational climate that promotes continuous learning experimentation, and innovation will provide a foundation for the library’s successful transition into the AI era.

Development of a Web-Based Application for Tracking Official Documents Using a Barcode System

Narakorn Phonharn — 2025-11-23

This research aimed to develop and evaluate a web application for supervising and monitoring official documents using barcodes. The objectives were to create a system that enhances document management efficiency and to assess user satisfaction and system performance. The sample group for system evaluation consisted of five information technology experts and five experts in official document administration. Additionally, forty-five supporting staff members working in a government agency in Nakhon Phanom Province were selected as users. Research instruments included a system efficiency assessment form and a user satisfaction questionnaire. Data were analyzed using descriptive statistics, including mean and standard deviation.

The results revealed that the overall efficiency of the system was rated at the highest level . The barcode generation and scanning functions obtained the highest mean score, followed by the speed of document retrieval, accuracy of data processing, and data management capability. User satisfaction was also rated at the highest level in all aspects . The highest satisfaction was related to the overall system performance, followed by its ability to facilitate document searches, reduce working time, and provide comprehensive and user-friendly design.

The findings suggest that the developed web application can effectively store and retrieve document data, allowing users to check document status anytime and anywhere. This contributes to improved efficiency in monitoring, verifying, and reducing errors in document management processes within government organizations.

An Integrated Data Mining and GIS Approach for Assessing Tourism Potential in Thailand’s Less Visited Areas

Pratueng Vongtong — 2025-11-23

Less visited areas are destinations that do not qualify as primary tourist attractions and have yet to attract large numbers of visitors. These areas have potential for development based on their strengths in culture, agriculture, community products, tourism, and food. They also provide convenient transportation and accessibility. In Thailand, there are 55 provinces classified as Less visited areas. This study aims to classify provinces by their social and economic potential using clustering techniques and to create a GIS model that maps secondary tourist destinations by potential groups. Data was collected from social media using web scraping methods, covering 2010-2019. The study calculated average values for three economic and social factors: provincial population, the number of tourists visiting each province, and tourism revenue per province. This data was then analyzed using data mining techniques and clustering methods to classify the tourism potential of Less visited areas into three levels: high, medium, and low potential, employing the K-Means clustering algorithm. Subsequently, a map model of secondary tourism province groups was developed for each region based on potential levels using a geographic information system.

The results show that the high potential group includes provinces located in the Northeast (5 provinces) and Central regions (4 provinces), as well as one province each from the North, East, West, and South regions. The medium group consists of provinces in the Northeast (11 provinces), North (7 provinces), Central (5 provinces), and West (1 province) regions. The low potential group represents provinces in the South (8 provinces), Central (3 provinces), East (3 provinces), and Northeast (2 provinces) regions.

Thais’ Satisfaction with the Electronic Guidebook Recommending Tourist Attractions Wat Yai Suwannaram Worawihan, Phetchaburi Province

Matthanaphon Kaeothong — 2025-11-23

This research aimed to assess user satisfaction with the electronic guidebook for Wat Yai Suwannaram Worawihan in Phetchaburi Province. Data were collected from a sample of 405 Thais who read the electronic guidebook via an online questionnaire. Data were analyzed

The results revealed that readers were highly satisfied with the electronic guidebook for Wat Yai Suwannaram Worawihan in Phetchaburi Province overall. When considering each aspect and ranking the means from highest to lowest, readers were highly satisfied with the electronic guidebook's quality, high with graphics, and high with content.

Information Needs on Internet of the Pastors’ Seed Church under the Evangelical Fellowship of Thailand

Sirinard Wongsawangsiri — 2025-12-17

The purposes of this research were to 1) investigate the pastors’ information needs and compare the needs of information on internet according to information content, information format, language, and information resources and 2) study the development guidelines for the Phetchaburi Seed Church website of 46 the pastors in Seed Church under The Evangelical Fellowship of Thailand. A questionnaire was developed to collect data, which were further analyzed by percentage, mean, standard deviation. Test assumptions with F-test values. The LSD test is a statistical method used to compare group means and determine significant differences between them.

The results revealed that the pastors’ information needs on the Internet is overall at a high level. It was found that there were arranged in order as follows: Information content, information resources, information format and information language. When considering by each aspect, it was found that 1) information content aspect, it was found items with the highest average were at high level arranged in order as follows 1.1) the Bible, how to study the Bible, interpreting the Bible 1.2) pastoral care of members, discipleship, counseling and solving life problems and 1.3) doing a mission, such as setting up a church Evangelism, etc. 2) information format aspect, when considering each item, it was found that the highest average were at high level arranged in order as follows 2.1) the full text content 2.2) sound and 2.3) multimedia and 3) language aspect, when considering each item, it was found at high level was Thai language 4) information resources aspect, when considering each type, it was found at the highest average was at high level, arranged in order as follows Christian organization and government agencies. The website development guidelines for the Phetchaburi Seed Church are that the website should contain content related to Bible verses, Bible lessons, pastoral care and counseling. The sermon lessons are in the form of videos and links to websites of Christian organizations and government agencies. The website is primarily in Thai language.

A Comparative Analysis of Models for Forecasting Thailand’s Unemployment Rate, 2021-2024

Sureenat Manola — 2025-12-23

This study aims to compare the performance of unemployment rate forecasting models, including the Autoregressive Integrated Moving Average (ARIMA), Holt’s Winters, K-Nearest Neighbors (K-NN), and Linear Regression models. The analysis is based on Thailand’s unemployment rate data obtained from the Department of Employment, consisting of provincial-level data from 77 provinces covering the period from 2021 to 2024. The objective is to evaluate the performance of each model and compare their forecasting accuracy. The results indicate that the ARIMA model yields the lowest Mean Absolute Error (MAE) of 6,658.515 and the lowest Root Mean Square Error (RMSE) of 8,578.801, reflecting lower numerical forecasting errors and greater stability. Although Holt’s Winters model achieves the lowest Mean Absolute Percentage Error (MAPE) at 4%, indicating high relative accuracy, its RMSE and MAE values remain higher than those of the ARIMA model. The K-Nearest Neighbors (K-NN) model shows a moderate MAPE of 6% but exhibits a very high RMSE of 62,036.073, suggesting instability in its forecasting results. Meanwhile, the Linear Regression model records a MAPE of 0%, but its RMSE and MAE values are abnormally high, indicating an overfitting problem and poor suitability for practical applications. Therefore, the findings conclude that the ARIMA model is the most appropriate approach for forecasting Thailand’s unemployment rate, as it provides the best balance between forecasting accuracy and numerical error.

Road Accident Severity Classification in Thailand Using K-Means Clustering and Decision Tree Techniques

Pranomkorn Ampornphan — 2025-12-24

This research aims to analyze road accident patterns in Thailand and identify factors influencing accident severity using data mining techniques, including K-Means clustering and Decision Tree classification. The dataset used in this study consists of 81,744 accident records obtained from the Open Government Data of Thailand.

The results of K-Means clustering indicate that the optimal number of clusters is four (k = 4), which effectively categorizes road accidents into four major groups: (1) Multi-vehicle accidents with moderate to high severity, (2) Minor accidents with low severity, (3) Fatal accidents with high severity, and (4) Injury-related accidents with moderate severity. Subsequently, a Decision Tree model was employed to extract decision rules (If–Then rules), where accident severity was defined as the target variable, while temporal factors, road characteristics, vehicle types, and environmental conditions were used as independent variables.

Model performance was evaluated using 10-fold cross-validation, which achieved an Accuracy of 85%, Precision of 85%, Recall of 85%, and an F1-score of 84%, indicating that the model is capable of effectively explaining road accident patterns. The findings of this study can serve as empirical evidence to support road safety policy formulation and the development of preventive measures by relevant authorities. Furthermore, this research provides guidelines for the future application of machine learning and deep learning techniques to enhance road safety management and accident prevention strategies.