• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.2
• /
• pp.379-386
• /
• 2014

As the use of mobile device is increasing rapidly, the number of users is also increasing. However, most of the app stores are using recommendation of simple ranking method, so the accuracy of recommendation is lower. To recommend an item that is more appropriate to the user, this paper proposes a technique that reflects the weight of user information and recent preference degree of item. The proposed technique classifies the data set by categories and then derives a predicted value by applying the user's information weight to the collaborative filtering technique. To reflect the recent preference degree of item by categories, the average of items' rating values in the designated period is computed. An item is recommended by combining the two result values. The experiment result indicated that the proposed method has been more enhanced the accuracy, appropriacy, compared to item-based, user-based method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.781-784
• /
• 2019

최근 AI를 산업 서비스에 적용하기 위해 많은 회사들이 활발히 연구를 하고 있다. 아마존과 넷플릭스 같은 거대 기업들은 이미 빅데이터와 AI 머신러닝을 이용한 추천 시스템을 구현하였고 아마존은 매출의 35%가 추천에 의해 발생하고 넷플릭스 75%의 사용자가 추천을 통해 영화를 선택한다고 보고되었다. 이러한 두 기업의 높은 추천 효율성의 이유는 협업 필터링(Collaborative filtering)과 같은 다양한 추천 알고리즘과 방대한 상품 및 고객 행동(구매, 시청 등) 데이터 등이 존재하고 있기 때문이다. 기계학습에서 알고리즘 학습을 위한 데이터의 양이 많지 않을 경우 알고리즘의 성능을 보장할 수 없다는 것이 일반적인 의견이다. 방대한 데이터를 가진 기업에서 추천 알고리즘을 적극적으로 활용 및 연구하고 있는 것도 이러한 이유 때문이다. 반면, 오프라인 및 여행사 기반에서 온라인 기반으로 영역을 차츰 확대하고 있는 항공 서비스 고객 데이터의 경우, 산업의 특성상 많은 회원에 비해 고객 1명당 온라인에서 활동하는 이력이 많지 않은 것이 특징이다. 이는, 추천 알고리즘을 통한 서비스 제공에서 큰 제약사항으로 작용한다. 본 연구에서는, 이러한 희박한 고객 활동 데이터에서 최신성 기반의 추천 시스템을 통하여 제약사항을 극복하고 추천 효율을 높이는 방법을 제안한다. 고객의 최근 접속 이력 로그를 시간 기준으로 데이터 셋을 분할하여 추천 알고리즘에 반영하였을 때, 추천된 노선에 대한 고객의 반응을 추천 성능 지표인 CTR(Click-Through Rate)로 측정하여 성능을 확인해 보았다.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.582-587
• /
• 2021

Book recommender system, which suggests book to users according to their book taste and preference effectively improves users' book-reading experience and exposes them to variety of books. Insufficient dataset of book rating records by users degrades the quality of recommendation. In this study, we suggest a book recommendation system that makes use of user's book ratings collaboratively with user's movie ratings where more abundant datasets are available. Through comprehensive experiment, we prove that our methods improve the recommendation quality and effectively recommends more diverse kind of books. In addition, this will be the first attempt for book recommendation system to utilize movie rating data, which is from the media-platform other than books.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.12
• /
• pp.259-266
• /
• 2023

In this paper, we propose an algorithm that can improve the accuracy performance of collaborative filtering using attribute-based opinion mining (ABOM). For the experiment, a total of 1,227 online consumer review data about smartphone apps from domestic smartphone users were used for analysis. After morpheme analysis using the KKMA (Kkokkoma) analyzer and emotional word analysis using KOSAC, attribute extraction is performed using LDA topic modeling, and the topic modeling results for each weighted review are used to add up the ratings of collaborative filtering and the sentiment score. MAE, MAPE, and RMSE, which are statistical model performance evaluations that calculate the average accuracy error, were used. Through experiments, we predicted the accuracy of online customers' app ratings (APP_Score) by combining traditional collaborative filtering among the recommendation algorithms and the attribute-based opinion mining (ABOM) technique, which combines LDA attribute extraction and sentiment analysis. As a result of the analysis, it was found that the prediction accuracy of ratings using attribute-based opinion mining CF was better than that of ratings implementing traditional collaborative filtering.

• Journal of Intelligence and Information Systems
• /
• v.21 no.2
• /
• pp.1-18
• /
• 2015

Collaborative filtering(CF) algorithm has been popularly used for recommender systems in both academic and practical applications. A general CF system compares users based on how similar they are, and creates recommendation results with the items favored by other people with similar tastes. Thus, it is very important for CF to measure the similarities between users because the recommendation quality depends on it. In most cases, users' explicit numeric ratings of items(i.e. quantitative information) have only been used to calculate the similarities between users in CF. However, several studies indicated that qualitative information such as user's reviews on the items may contribute to measure these similarities more accurately. Considering that a lot of people are likely to share their honest opinion on the items they purchased recently due to the advent of the Web 2.0, user's reviews can be regarded as the informative source for identifying user's preference with accuracy. Under this background, this study proposes a new hybrid recommender system that combines with users' review mining. Our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and his/her text reviews on the items when calculating similarities between users. In specific, our system creates not only user-item rating matrix, but also user-item review term matrix. Then, it calculates rating similarity and review similarity from each matrix, and calculates the final user-to-user similarity based on these two similarities(i.e. rating and review similarities). As the methods for calculating review similarity between users, we proposed two alternatives - one is to use the frequency of the commonly used terms, and the other one is to use the sum of the importance weights of the commonly used terms in users' review. In the case of the importance weights of terms, we proposed the use of average TF-IDF(Term Frequency - Inverse Document Frequency) weights. To validate the applicability of the proposed system, we applied it to the implementation of a recommender system for smartphone applications (hereafter, app). At present, over a million apps are offered in each app stores operated by Google and Apple. Due to this information overload, users have difficulty in selecting proper apps that they really want. Furthermore, app store operators like Google and Apple have cumulated huge amount of users' reviews on apps until now. Thus, we chose smartphone app stores as the application domain of our system. In order to collect the experimental data set, we built and operated a Web-based data collection system for about two weeks. As a result, we could obtain 1,246 valid responses(ratings and reviews) from 78 users. The experimental system was implemented using Microsoft Visual Basic for Applications(VBA) and SAS Text Miner. And, to avoid distortion due to human intervention, we did not adopt any refining works by human during the user's review mining process. To examine the effectiveness of the proposed system, we compared its performance to the performance of conventional CF system. The performances of recommender systems were evaluated by using average MAE(mean absolute error). The experimental results showed that our proposed system(MAE = 0.7867 ~ 0.7881) slightly outperformed a conventional CF system(MAE = 0.7939). Also, they showed that the calculation of review similarity between users based on the TF-IDF weights(MAE = 0.7867) leaded to better recommendation accuracy than the calculation based on the frequency of the commonly used terms in reviews(MAE = 0.7881). The results from paired samples t-test presented that our proposed system with review similarity calculation using the frequency of the commonly used terms outperformed conventional CF system with 10% statistical significance level. Our study sheds a light on the application of users' review information for facilitating electronic commerce by recommending proper items to users.

• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.57-77
• /
• 2013

Social media has become one of the most popular media in web and mobile application. In 2011, social networks and blogs are still the top destination of online users, according to a study from Nielsen Company. In their studies, nearly 4 in 5active users visit social network and blog. Social Networks and Blogs sites rule Americans' Internet time, accounting to 23 percent of time spent online. Facebook is the main social network that the U.S internet users spend time more than the other social network services such as Yahoo, Google, AOL Media Network, Twitter, Linked In and so on. In recent trend, most of the companies promote their products in the Facebook by creating the "Facebook Page" that refers to specific product. The "Like" option allows user to subscribed and received updates their interested on from the page. The film makers which produce a lot of films around the world also take part to market and promote their films by exploiting the advantages of using the "Facebook Page". In addition, a great number of streaming service providers allows users to subscribe their service to watch and enjoy movies and TV program. They can instantly watch movies and TV program over the internet to PCs, Macs and TVs. Netflix alone as the world's leading subscription service have more than 30 million streaming members in the United States, Latin America, the United Kingdom and the Nordics. As the matter of facts, a million of movies and TV program with different of genres are offered to the subscriber. In contrast, users need spend a lot time to find the right movies which are related to their interest genre. Recent years there are many researchers who have been propose a method to improve prediction the rating or preference that would give the most related items such as books, music or movies to the garget user or the group of users that have the same interest in the particular items. One of the most popular methods to build recommendation system is traditional Collaborative Filtering (CF). The method compute the similarity of the target user and other users, which then are cluster in the same interest on items according which items that users have been rated. The method then predicts other items from the same group of users to recommend to a group of users. Moreover, There are many items that need to study for suggesting to users such as books, music, movies, news, videos and so on. However, in this paper we only focus on movie as item to recommend to users. In addition, there are many challenges for CF task. Firstly, the "sparsity problem"; it occurs when user information preference is not enough. The recommendation accuracies result is lower compared to the neighbor who composed with a large amount of ratings. The second problem is "cold-start problem"; it occurs whenever new users or items are added into the system, which each has norating or a few rating. For instance, no personalized predictions can be made for a new user without any ratings on the record. In this research we propose a clustering method according to the users' genre interest extracted from social network service (SNS) and user's movies rating information system to solve the "cold-start problem." Our proposed method will clusters the target user together with the other users by combining the user genre interest and the rating information. It is important to realize a huge amount of interesting and useful user's information from Facebook Graph, we can extract information from the "Facebook Page" which "Like" by them. Moreover, we use the Internet Movie Database(IMDb) as the main dataset. The IMDbis online databases that consist of a large amount of information related to movies, TV programs and including actors. This dataset not only used to provide movie information in our Movie Rating Systems, but also as resources to provide movie genre information which extracted from the "Facebook Page". Formerly, the user must login with their Facebook account to login to the Movie Rating System, at the same time our system will collect the genre interest from the "Facebook Page". We conduct many experiments with other methods to see how our method performs and we also compare to the other methods. First, we compared our proposed method in the case of the normal recommendation to see how our system improves the recommendation result. Then we experiment method in case of cold-start problem. Our experiment show that our method is outperform than the other methods. In these two cases of our experimentation, we see that our proposed method produces better result in case both cases.

• The Journal of Society for e-Business Studies
• /
• v.15 no.3
• /
• pp.131-145
• /
• 2010

Until now, popular paradigms to provide e-catalog documents that are adapted to users' needs are keyword search or collaborative filtering based recommendation. Since users' queries are too short to represent what users want, it is hard to provide the users with e-catalog documents that are adapted to their needs(i.e., queries and preferences). Although various techniques have beenproposed to overcome this problem, they are based on index term matching. A conventional Bayesian belief network-based approach represents the users' needs and e-catalog documents with their corresponding concepts. However, since the concepts are the index terms that are extracted from the e-catalog documents, it is hard to represent relationships between concepts. In our work, we extend the conventional Bayesian belief network based approach to represent users' needs and e-catalog documents with a concept network which is derived from the Web directory. By exploiting the concept network, it is possible to search conceptually relevant e-catalog documents although they do not contain the index terms of queries. Furthermore, by computing the conceptual similarity between users, we can exploit a semantic collaborative filtering technique for recommending e-catalog documents.

• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.526-529
• /
• 2003

Recommender systems or collaborative filtering are methods to identify potentially interesting or valuable items to a particular user Under the assumption that people with similar interest tend to like the similar types of items, these methods use a database on the preference of a set of users and predict the rating on the items that the user has not rated. Usually the preference of a particular user is liable to vary with time and this temporal variation may cause an inaccurate identification and prediction. In this paper we propose a method to adapt the temporal variation of the user preference in order to improve the predictive performance of a collaborative filtering algorithm. To be more specific, the correlation weight of the GroupLens system which is a general formulation of statistical collaborative filtering algorithm is modified to reflect only recent similarity between two user. The proposed method is evaluated for EachMovie dataset and shows much better prediction results compared with GrouPLens system.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.265-274
• /
• 2021

In this paper, we propose a novel recommendation model based on Doc2vec using search keywords and product details. Until now, a lot of prior studies on recommender systems have proposed collaborative filtering (CF) as the main algorithm for recommendation, which uses only structured input data such as customers' purchase history or ratings. However, the use of unstructured data like online customer review in CF may lead to better recommendation. Under this background, we propose to use search keyword data and product detail information, which are seldom used in previous studies, for product recommendation. The proposed model makes recommendation by using CF which simultaneously considers ratings, search keywords and detailed information of the products purchased by customers. To extract quantitative patterns from these unstructured data, Doc2vec is applied. As a result of the experiment, the proposed model was found to outperform the conventional recommendation model. In addition, it was confirmed that search keywords and product details had a significant effect on recommendation. This study has academic significance in that it tries to apply the customers' online behavior information to the recommendation system and that it mitigates the cold start problem, which is one of the critical limitations of CF.