KMITL

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

Browse

Settings

Subject: search.filters.subject.Opinion mining

Search Results

Now showing 1 - 4 of 4
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Multi-Label Classification of Foreign Tourists' Opinions on Thailand Tourism Development
    (2024-10-03)
    Suramanka, Lalita
    ;
    Hanskunatai, Anantaporn
    The enhancement of tourism quality in Thailand through the understanding and utilization of foreign tourists' opinions presents challenges due to the extensive volume of data involved. This research proposes a two-fold approach to address this issue: (1) the development of an opinion classification model, and (2) the analysis of tourists' opinions through a dashboard. A dataset, compiled by the Tourism Authority of Thailand (TAT) and consisting of opinions from foreign tourists regarding areas for improvement in Thai tourism, was utilized. A total of 2,249 comments were collected. Experimental results demonstrate that the use of data augmentation, feature selection, Multi-label transformation using Classifier Chains, and the Random Forest classification model on the training dataset yields promising results with an accuracy rate of 80%, precision of 90%, recall of 81%, F1-score of 85%, and Hamming loss of 0.04. Analysis from the dashboard revealed the top three key areas for improvement: communication/language, traffic/public transportation, and cleanliness/hygiene.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    The ensemble of Naïve Bayes classifiers for hotel searching
    (2014-01-01)
    Srisuan, Janasthar
    ;
    Hanskunatai, Anantaporn
    The objective of the paper is to present a new ensemble of Naïve Bayes classifiers model for an application of hotel searching. The dataset were collected from 293 reviews of 15 hotels in Phuket. The main idea of the proposed model is to combine two models of Naïve Bayes classifiers with different feature selection techniques. The output of the searching model is a list of hotel names ranking by hotel probability related to user keywords. The searching performance of the ensemble model was compared with two classical searching methods: Boolean searching and Boyer-Moore searching. The results show that the ensemble of Naïve Bayes classifiers model provides the highest average rank-accuracy. In addition, the proposed model also takes the fastest time in searching when compared with the other techniques.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Extracting product features and opinions from product reviews using dependency analysis
    (2010-11-29)
    Somprasertsri, Gamgarn
    ;
    Lalitrojwong, Pattarachai
    In web pages, the reviews are written in natural language and are unstructured-free-texts scheme. Online product reviews is considered as a significant informative resource which is useful for both potential customers and product manufacturers. The task of manually scanning through large amounts of review one by one is computational burden and is not practically implemented with respect to businesses and customer perspectives. Therefore it is more efficient to automatically process the various reviews and provide the necessary information in a suitable form. The task of product feature and opinion is to find product features that customers refer to their topic reviews. It would be useful to characterize the opinions about product. In this paper, we propose an approach to extract product features and to identify the opinions associated with these features from reviews through syntactic information based on dependency analysis. ©2010 IEEE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Mining feature-opinion in online customer reviews for opinion summarization
    (2010-06-18)
    Somprasertsri, Gamgarn
    ;
    Lalitrojwong, Pattarachai
    Online customer reviews is considered as a significant informative resource which is useful for both potential customers and product manufacturers. In web pages, the reviews are written in natural language and are unstructured-free-texts scheme. The task of manually scanning through large amounts of review one by one is computational burden and is not practically implemented with respect to businesses and customer perspectives. Therefore it is more efficient to automatically process the various reviews and provide the necessary information in a suitable form. The high-level problem of opinion summarization addresses how to determine the sentiment, attitude or opinion that an author expressed in natural language text with respect to a certain feature. In this paper, we dedicate our work to the main subtask of opinion summarization. The task of product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the performance of opinion orientation identification. It is important to properly identify the semantic relationships between product features and opinions. We proposed an approach for mining product feature and opinion based on the consideration of syntactic information and semantic information. By applying dependency relations and ontological knowledge with probabilistic based model, the result of our experiments shows that our approach is more flexible and effective. © J.UCS.