Abstract
As the importance of providing personalized services increases, various studies on personalized recommendation systems are actively being conducted. Among the many methods used for recommendation systems, the most widely used is collaborative filtering. However, this method has lower accuracy because recommendations are limited to using quantitative information, such as user ratings or amount of use. To address this issue, many studies have been conducted to improve the accuracy of the recommendation system by using other types of information, in addition to quantitative information. Although conducting sentiment analysis using reviews is popular, previous studies show the limitation that results of sentiment analysis cannot be directly reflected in recommendation systems. Therefore, this study aims to quantify the sentiments presented in the reviews and reflect the results to the ratings; that is, this study proposes a new algorithm that quantifies the sentiments of user-written reviews and converts them into quantitative information, which can be directly reflected in recommendation systems. To achieve this, the user reviews, which are qualitative information, must first be quantified. Thus, in this study, sentiment scores are calculated through sentiment analysis by using a text mining technique. The data used herein are from movie reviews. A domain-specific sentiment dictionary was constructed, and then based on the dictionary, sentiment scores of the reviews were calculated. The collaborative filtering of this study, which reflected the sentiment scores of user reviews, was verified to demonstrate its higher accuracy than the collaborative filtering using the traditional method, which reflects only user rating data. To overcome the limitations of the previous studies that examined the sentiments of users based only on user rating data, the method proposed in this study successfully enhanced the accuracy of the recommendation system by precisely reflecting user opinions through quantified user reviews. Based on the findings of this study, the recommendation system accuracy is expected to improve further if additional analysis can be performed.
Highlights
It is estimated that more than 2.5 trillion MB of data are generated per day worldwide, at the current pace, and the pace of this generation is increasing by 60% each year
The same rating scores of 10 points may be given by a user to two different movies, the intensity of the sentiments found in the user review texts may be different for these movies
Using the described mean absolute error (MAE) and root-mean-square error (RMSE), the performances of the existing method using only ratings for prediction and the prediction method proposed in this paper were compared
Summary
It is estimated that more than 2.5 trillion MB of data are generated per day worldwide, at the current pace, and the pace of this generation is increasing by 60% each year. The necessity of a recommendation system that can remove unnecessary information from a large of number data and provide information according to individual preferences is gradually increasing. Previous studies on recommendation systems that provided personalized information to users were generally focused on analyses using structured data, which are easy to quantify, such as user purchase history, product ratings, and number of visits [1]. In recent years, recommendations limited to using only the user rating data as the index to indicate user preferences provided low accuracy [2,3]. This indicates that there were limitations in recommendation system developments as the detailed and elaborate preferences of users are not reflected. Despite the same quantitative rating scores, this could be the crucial factor that reduces the accuracy of the recommendation system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
