International Journal on Advanced Science, Engineering and Information Technology, Vol. 13 (2023) No. 4, pages: 1546-1553, DOI:10.18517/ijaseit.13.4.17369

Customer Needs Classification from Online Social Media Using Bag-of-Concepts Representation

Kanjana Laosen, Adisak Intana, Phisitchai Chuaynukul


Social media platforms are now a very powerful tool for digital marketing strategy because it helps companies to be in direct contact with their customers. A communication problem in digital social media is several customer needs phrases posted on social media, making it difficult for businesses to find relevant posts and respond to customers immediately. Therefore, knowing and understanding the customer requirements for a product can help the product owner to propose the right product to the right customer. This study focuses on understanding customer needs in Thai and classifying them into certain concepts. This study aims to classify customer needs for products in online social media community groups. The model focuses on understanding Thai customer need phrases. We then use a bag of concepts representation, including pattern analysis that applies n-grams together with POS and synonym replacement, conceptual analysis, pattern matching, and class labeling that applies concept sets obtained from the FP-Growth algorithm and represents TD-IDF value in a bag of concepts. The effectiveness of the proposed model is evaluated on five classification algorithms, including Decision Tree, Support Vector Machine, Naïve-Bayes, K-Nearest Neighbor, and RBF Neural Network. The results show that Decision Tree can yield higher accuracy and F-measure values than the others. As this study is an initial step of a personalized product recommendation system in the future, this study will apply the model to the remaining domains for future work.


Conceptual level analysis; the bag of concepts; online social media; customer needs classification

Viewed: 226 times (since abstract online)

cite this paper     download