Digital Library[ Search Result ]
Review-based Personalized Recommendation System using Effective Personalized Fusion and BERT
http://doi.org/10.5626/JOK.2023.50.8.646
Generally, review texts contain personal information from users, and reviews written by users can have different meanings, even if they use the exact wording. These review features can be used to compensate for the shortcomings of collaborative filtering, which is vulnerable to data sparsity. They can also be used as information for personalized recommendation systems. Despite the success of pre-trained language models in natural language processing, there has been little research on personalized recommendation systems that leverage BERT to enrich individual user features from reviews. In this work, we propose a rating prediction model that uses BERT for detailed learning of user and item-specific features from reviews and tightly combine them with user and product IDs to represent personalized user and item. Experiments results show that the proposed model can achieve improved performance over the baseline on the Amazon benchmark dataset.
Aspect Summarization for Product Reviews based on Attention-based Aspect Extraction
Jun-Nyeong Jeong, Sang-Young Kim, Seong-Tae Kim, Jeong-Jae Lee, Yuchul Jung
http://doi.org/10.5626/JOK.2021.48.12.1318
Recently, document summaries such as articles and papers through machine learning and summary-related research on online reviews are active. In this study, unlike the existing simply summarizing content, a technique was developed for generating an aspect summary by considering various aspects of product reviews. By refining the earphone product review data crawled to build the learning data, 40,000 reviews were obtained. Moreover, we manually constructed 4,000 aspect summaries to be used for our training and evaluation tasks. In particular, we proposed a model that could summarize aspects using only text data using the aspect-based word expansion technique (ABAE). To judge the effectiveness of the proposed technique, we performed experiments according to the use of words related to aspects and the masking ratio during learning. As a result, it was confirmed that the model that randomly masked 25% of the words related to the aspect showed the highest performance, and during verification, the ROUGE was 0.696, and the BERTScore was 0.879.
Korean Movie Review Sentiment Analysis using Self-Attention and Contextualized Embedding
Cheoneum Park, Dongheon Lee, Kihoon Kim, Changki Lee, Hyunki Kim
http://doi.org/10.5626/JOK.2019.46.9.901
Sentiment analysis is the processing task that involves collecting and classifying opinions about a specific object. However, it is difficult to grasp the subjectivity of a person using natural language, so the existing sentimental word dictionaries or probabilistic models cannot solve such a task, but the development of deep learning made it possible to solve the task. Self-attention is a method of modeling a given input sequence by calculating the attention weight of the input sequence itself and constructing a context vector with a weighted sum. In the context, a high weight is calculated between words with similar meanings. In this paper, we propose a method using a modeling network with self-attention and pre-trained contextualized embedding to solve the sentiment analysis task. The experimental result shows an accuracy of 89.82%.
Evaluation of Korean Reviews Automatically Generated using Long Short-Term Memory Unit
http://doi.org/10.5626/JOK.2019.46.6.515
Opinion Spam is the act of misleading the public to comply with the intent of a particular group. This is a serious problem at this point in time, when online services are widely deployed and the reputation of a specific target seller relative to the offline market can be easily affected. In this context, detecting and preventing opinion spam is an important research topic. This study investigates the current status of the domestic online market and poses possible damages caused by opinion spam through the automatic generation of Korean reviews using a recurrent neural network (RNN). In particular, we applied a learning model based on an LSTM (long short-term memory) unit for the Korean language in order to improve the long-term dependency problem of the typical RNN. Then, the Word2Vec is exploited to improve the relevance by replacing keywords with a set of candidates from the target market. We show the translation of the learning model based on a foreign language to Korean, then evaluate its appropriateness with regard to the development of countermeasures with which to effectively prevent automatically generated opinion spam in the near future.
Enhancing the Performance of Recommender Systems Using Online Review Clusters
Giseop Noh, Hayoung Oh, Jaehoon Lee
http://doi.org/10.5626/JOK.2018.45.2.126
The recommender system (RS) has emerged as a solution to overcome the constraints of excessive information provision and to maximize profit and reputation for information providers. Although the RS can be implemented with various approaches, there is no study on how to appropriately utilize the information generated from the review of the recommended object. We propose a method to improve the performance of RS by using cluster information generated from online review. We implemented the proposed method and experimented with real data, and confirmed that the performance is significantly improved compared to the existing approaches.
Performance Evaluation of Review Spam Detection for a Domestic Shopping Site Application
As the number of customers who write fake reviews is increasing, online shopping sites have difficulty in providing reliable reviews. Fake reviews are called review spam, and they are written to promote or defame the product. They directly affect sales volume of the product; therefore, it is important to detect review spam. Review spam detection methods suggested in prior researches were only based on an international site even though review spam is a widespread problem in domestic shopping sites. In this paper, we have presented new review features of the domestic shopping site NAVER, and we have applied the formerly introduced method to this site for performing an evaluation.
Automatic Product Review Helpfulness Estimation based on Review Information Types
Many available online product reviews for any given product makes it difficult for a consumer to locate the helpful reviews. The purpose of this study was to investigate automatic helpfulness evaluation of online product reviews according to review information types based on the target of information. The underlying assumption was that consumers find reviews containing specific information related to the product itself or the reliability of reviewers more helpful than peripheral information, such as shipping or customer service. Therefore, each sentence was categorized by given information types, which reduced the semantic space of review sentences. Subsequently, we extracted specific information from sentences by using a topic-based representation of the sentences and a clustering algorithm. Review ranking experiments indicated more effective results than other comparable approaches.
Automatic Construction of a Negative/positive Corpus and Emotional Classification using the Internet Emotional Sign
Kyoungae Jang, Sanghyun Park, Woo-Je Kim
Internet users purchase goods on the Internet and express their positive or negative emotions of the goods in product reviews. Analysis of the product reviews become critical data to both potential consumers and to the decision making of enterprises. Therefore, the importance of opinion mining techniques which derive opinions by analyzing meaningful data from large numbers of Internet reviews. Existing studies were mostly based on comments written in English, yet analysis in Korean has not actively been done. Unlike English, Korean has characteristics of complex adjectives and suffixes. Existing studies did not consider the characteristics of the Internet language. This study proposes an emotional classification method which increases the accuracy of emotional classification by analyzing the characteristics of the Internet language connoting feelings. We can classify positive and negative comments about products automatically using the Internet emoticon. Also we can check the validity of the proposed algorithm through the result of high precision, recall and coverage for the evaluation of this method.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr