Chotipant, Supannada

Preferred name

Alternative Name

Chotiphan, Supannada

Main Affiliation

School of Information Technology

supannada.ch@kmitl.ac.th

Now showing 1 - 10 of 13

Some of the metrics are blocked by your
consent settings
Text Sentiment Analysis for Thailand Tourism Recommendation
(2025-01-01)
Boonyarakthunya, Ittichai
;
Chotipant, Supannada
Thailand is one of the world's most popular travel destinations. In the digital age, online reviews written by previous travelers have become a highly influential information source for decision-making. Unfortunately in many cases, users do not assign ratings, or the platforms do not require them. As a result, these systems are unable to process sentiment effectively from the textual reviews. Moreover, most existing recommendation systems lack the ability to group destinations with similar characteristics or categories. This paper proposes a tourism recommendation system that integrates sentiment analysis with tag clustering. The system is capable of processing both user sentiment and destination-related content, enabling it to generate personalized recommendations that align with users' preferences and emotional context. The experimental results show that the SVM model achieved an average sentiment classification accuracy of 94%. In contrast, tag clustering using DBSCAN presented a limitation in the form of high noise levels-over 30% of tags were classified as noise (represented by cluster -1), indicating that a significant number of tags could not be assigned to any meaningful cluster. This reflects a limitation in tag coverage and suggests that further refinement is needed to improve grouping performance in real-world datasets with diverse and contextually ambiguous descriptions.
Some of the metrics are blocked by your
consent settings
Semantic-based Thai Recipe Recommendation
(2022-01-01)
Chotipant, Supannada
Nowadays, people are constantly affected by epidemics such as COVID-19. To reduce the risk of acquiring germs in the community, people's lifestyles have been changed, and they are more inclined to cook for themselves. Typically, people can usually quickly and easily find recipe information via websites and applications. The resulting recipes consist of ingredients as specified by the user. Unfortunately, users often have ingredients that disappear in available cooking recipes. This makes the system is unable to recommend all relevant recipes to users, although the users can use the existing ingredients instead of the ingredients specified in the recipes. Based on this limitation, this research proposes a semantic-based Thai cooking recipe recommendation system which can recommend recipes based on the ingredient substitutes. This research uses existing Thai food ontology to retrieve substitute ingredients based on three different ingredient properties, such as smell, taste, and texture. To recommend cooking recipes, the system expands the given user queries with substitute ingredients and then calculates similarities between all queries and each cooking recipe. Recipes with high similarities are presented and ranked to users. To evaluate the performances, precision, recall and f-measure are applied. The experiments demonstrate that the proposed method performs well with 0.96, 0.72, and 0.82 in precision, recall, and f-measure respectively.
Some of the metrics are blocked by your
consent settings
Emotion-based music player
(2019-07-01)
Chankuptarat, Krittrin
;
Sriwatanaworachai, Raphatsak
;
Chotipant, Supannada
Nowadays, people tend to increasingly have more stress because of the bad economy, high living expenses, etc. Listening to music is a key activity that assists to reduce stress. However, it may be unhelpful if the music does not suit the current emotion of the listener. Moreover, there is no music player which is able to select songs based on the user emotion. To solve this problem, this paper proposes an emotion-based music player, which is able to suggest songs based on the user's emotions; sad, happy, neutral and angry. The application receives either the user's heart rate or facial image from a smart band or mobile camera. It then uses the classification method to identify the user's emotion. This paper presents 2 kinds of the classification method; the heart rate-based and the facial image-based methods. Then, the application returns songs which have the same mood as the user's emotion. The experimental results show that the proposed approach is able to precisely classify the happy emotion because the heart rate range of this emotion is wide.
Some of the metrics are blocked by your
consent settings
A Personalized Food Recommendation Chatbot System for Diabetes Patients
(2020-01-01)
Thongyoo, Phupat
;
Anantapanya, Phuttipong
;
Jamsri, Pornsuree
;
Chotipant, Supannada
Diabetes is a disorder of the body that is unable to produce enough insulin. Diabetes causes the body to improperly burn sugar, which affects the blood sugar level leaving a sugar residue. Diabetes is related to genes, body weight, lack of exercise and aging. When patients with diabetes neglect good nutrition this can cause many health problems. This research, therefore, develops a chatbot named “Waan-Noy” to recommend a diet suitable for individuals with diabetes and build a cooperative health society. Our chatbot recommends personalized eating. It is suitable for use by diabetes patients as indicated by their evaluations. Through use of nutrition therapy controls, Waan-Noy recommends specific foods. The user’s evaluation is divided into 3 areas: content, design, and implementation to determine user degree of satisfaction with Waan-Noy.
Some of the metrics are blocked by your
consent settings
Examining the critical success factors of startup in Thailand using structural equation model
(2018-11-13)
Nalintippayawong, Srinual
;
Waiyawatpattarakul, Nattakit
;
Chotipant, Supannada
Startup is a fast-growing business model by funding from investors, however, it also has a high failure rate and risk. This research aims to examine critical success factors of and their relations in Thai startups. Structural equation model is applied for studying causal relationships between factors by using factor analysis and multivariable regression analysis. Based on sixteen observed variables, the results show that there are four critical success factors of Thai startups, namely support partner, business model, market opportunity, and customer perspective. Especially, the factors of the business model and support partner have direct effects on potential and success in startups. This research is a knowledge framework which assists, not only young startups to succeed their business, but also investors to evaluate investments in startups. Moreover, the paper also provides a literature review which is useful for researchers in the area of a startup.
Some of the metrics are blocked by your
consent settings
Application of Large Language Models for Aspect-Based Sentiment Analysis on Social Media Data: A Case Study of the Thai Telecommunications Industry
(2026-01-01)
Limseesawan, Krittapas
;
Netisopakul, Ponrudee
;
Chotipant, Supannada
;
Voravuthikunchai, Winn
;
Sirivorachodphokin, Thitirat
Social media is a valuable source of consumer opinion data, particularly in Thailand's highly competitive telecommunications market among AIS, TRUE, and DTAC. This study compares three LLM-based approaches for Aspect-Based Sentiment Analysis (ABSA) on 3,508 Thai-language messages from Pantip.com and YouTube.com: (1) Prompt Engineering, (2) Domain Adaptation & Fine-Tuning, and (3) Multi-Agent Debate Framework. Results show that Domain Adaptation & Fine-Tuning achieves the best accuracy-latency trade-off, with Qwen2.5-1.5B-Instruct exceeding 87% average accuracy in under 4 seconds per message. Multi-Agent Debate achieves the highest Category accuracy (82.82%) but at a latency cost of 10-16 seconds per message. Gemini-2.5-Flash-Lite provides the best speed-accuracy balance for Prompt Engineering without additional training. Critically, small open-source models (1B-1.5B parameters) subjected to domain-specific fine-tuning can approach or surpass proprietary large models on this task, suggesting domain alignment may outweigh raw parameter scale for narrow, well-defined ABSA tasks.
Some of the metrics are blocked by your
consent settings
A system for research community annotation
(2017-08-25)
Chotipant, Supannada
Community detection as an important task that allows understanding of complex networks has attracted much research attention. However, existing research stops at uncovering the community structures, from which the semantic meaning of individual communities cannot be inferred directly. This paper proposes to semantically annotate communities detected in a network. In particular, a system for annotating the research communities in a bibliographic network is developed. An unsupervised method is adopted to generate annotations according to three criteria, 1) the annotations should be semantically relevant with the community, 2) the annotations should be discriminative across communities, and 3) the annotations should have high topic coverage. The system shows that the generated annotations effectively enable the interpretation and understanding of large and various research communities, advancing existing research into community detection for community comprehension.
Some of the metrics are blocked by your
consent settings
Stock Price Prediction from Multi Data Sources Using LSTM, FinBERT and BERTweet
(2026-06-16)
Auensupa, Suchart
;
Netisopakul, Ponrudee
;
Chotipant, Supannada
This research presents a stock price forecasting approach for technology sector companies Apple, Amazon and Tesla. The study begins by comparing a statistical model (ARIMA) with a deep learning model (LSTM) to identify the best-performing model, which is then used as the baseline for stock price forecasting. The approach integrates data from multiple sources, including numerical time series data and textual data. Numerical inputs consist of open, high, and low prices, which are used to forecast the closing price. Technical indicator features are subsequently added to enhance the model's predictive capability. Finally, textual data from economic news and Twitter social media reflecting market sentiment are incorporated. News sentiment is analyzed using the FinBERT model, while sentiment from social media data is evaluated using the BERTweet model. The resulting sentiment features are then combined with the numerical data and all inputs are processed using the LSTM model. Experimental results show that incorporating technical indicator features improves forecasting accuracy by an average of 17%. Furthermore, integrating textual data from news improves accuracy by an additional 6%, resulting in an overall performance improvement of up to 23%. These findings demonstrate the value of integrating multi-source data and highlight the important role of textual information in enhancing stock price forecasting performance.
Some of the metrics are blocked by your
consent settings
Adapted ACO Algorithm for Energy-Efficient Path Finding of Waste Collection Robot
(2022-01-01)
Tomitagawa, Koki
;
Anuntachai, Anuntapat
;
Chotiphan, Supannada
;
Wongwirat, Olarn
;
Kuchii, Shigeru
Waste collection is a major concern of many companies with large areas of facility, e.g., buildings or factories, where there are many trash bins at various dumping points. Therefore, they require human labor to handle, which is a major cost of consideration. Currently, there are research works using robots for waste collection instead of humans. There is a challenge for waste collection robots in terms of energy consumption to pick up the waste at various dumping points efficiently. The factors related to the energy consumption of waste collection robots are directly related to the distance and waste weight that the robots have to collect and carry from the trash bins at various dump points along the paths. This paper presents the adapted ant colony optimization (ACO) algorithm to find the energy-efficient paths of the waste collection robots. The adapted ACO algorithm uses the waste weight in the trash bin as path heuristic information between two dumping points to determine the state transition probability for finding the most energy-efficient path. The experiment was conducted by the simulation to compare the result with the conventional ACO algorithm that uses distance as the path heuristic information. The simulation results expressed that the adapted ACO algorithm provided the most energy-efficient path under the number of nodes and waste weights specified better than the conventional ACO algorithm.
Some of the metrics are blocked by your
consent settings
Development of WLAN Topology Display System
(2023-01-01)
Wongwirat, Olarn
;
Chotiphan, Supannada
;
Hongtong, Tadchapon
;
Suttijumnong, Nattawat
Currently, packet sniffer tools can capture packets and provide information for monitoring, analyzing, and troubleshooting networks, e.g., traffic, bandwidth, protocol, etc. However, these tools lack the capability, or feature, to display a network topology diagram on the screen, particularly for a WLAN (Wireless Local Area Network), which is different from expensive network monitoring software sold commercially in the market. Therefore, it is difficult for a network administrator to visualize which client is connected to which AP (Access point) in the service areas of WLAN, or hotspots, for monitoring. This paper presents the development of the WLAN topology display system to support the network administrator in monitoring and enhancing the network services in the future. The system acquires the packet data captured by the packet sniffer tool, i.e., Wireshark. Then, the packet information is analyzed by using the data from the MAC (Medium Access Control) header following the IEEE802.11 standard to find the types, connection modes, and MAC addresses. Finally, the mapping table associated with the connected devices, i.e., client stations and APs, is constructed and used to create the WLAN topology diagram to display on the screen. The prototype system is implemented and tested in the laboratory environment, and the WLAN topology diagram showing the connections between the clients and the APs can be displayed on screen accurately as required.

Chotipant, Supannada

Filters

Settings

Sort By

Results per page