• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.1242-1250
• /
• 2022

When recommending cold items that do not have user-item interactions to users, even we adopt state-of-the-arts algorithms, the predicted information of cold items tends to have lower accuracy compared to warm items which have enough user-item interactions. The lack of information makes for recommender systems to recommend monotonic items which have a few top popular contents matched to user preferences. As a result, under-diversified items have a negative impact on not only recommendation diversity but also on recommendation accuracy when recommending cold items. To address the problem, we adopt a diversification algorithm which tries to make distributions of accumulated contents embedding of the two items groups, recommended items and the items in the target user's already interacted items, similar. Evaluation on a real world data set CiteULike shows that the proposed method improves not only the diversity but also the accuracy of cold item recommendation.

• 대한산업공학회지
• /
• 제41권2호
• /
• pp.128-136
• /
• 2015

With the recent interests with culture technologies, many studies for recommendation systems have been done. In this vein, various music recommendation systems have been developed. However, they have often focused on the technical aspects such as feature extraction and similarity comparison, and have not sufficiently addressed them in user-centered perspectives. For users' high satisfaction with recommended music items, it is necessary to study how the items are connected to the users' actual desires. For this, our study proposes a novel music recommendation method based on serendipity, which means the freshness users feel for their familiar items. The serendipity is measured through the comparison of users' past and recent listening tendencies. We utilize neural networks to apply these tendencies to the recommendation process and to extract the features of music items as MFCCs (Mel-frequency cepstral coefficients). In that the recommendation method is developed based on the characteristics of user behaviors, it is expected that user satisfaction for the recommended items can be actually increased.

• Journal of Information Technology Applications and Management
• /
• 제21권4호
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.1-19
• /
• 2021

The graph-based tag recommendation algorithm FolkRank can effectively utilize the relationships between three entities, namely users, items and tags, and achieve better tag recommendation performance. However, FolkRank does not consider the internal relationships of user-user, item-item and tag-tag. This leads to the failure of FolkRank to effectively map the tagging behavior which contains user neighbors and item neighbors to a tripartite graph. For item-item relationships, we can dig out items that are very similar to the target item, even though the target item may not have a strong connection to these similar items in the user-item-tag graph of FolkRank. Hence this paper proposes an improved FolkRank algorithm named FolkRank++, which fully considers the user-user and item-item internal relationships in tag recommendation by adding the correlation information between users or items. Based on the traditional FolkRank algorithm, an initial weight is also given to target user and target item's neighbors to supply the user-user and item-item relationships. The above work is mainly completed from two aspects: (1) Finding items similar to target item according to the attribute information, and obtaining similar users of the target user according to the history behavior of the user tagging items. (2) Calculating the weighted degree of items and users to evaluate their importance, then assigning initial weights to similar items and users. Experimental results show that this method has better recommendation performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.5826-5841
• /
• 2019

In our previous research, we proposed a tag emotion-based item recommendation scheme. The ternary associations among users, items, and tags are described as a three-order tensor in order to capture the emotions in tags. The candidates for recommendation are created based on the latent semantics derived by a high-order singular value decomposition technique (HOSVD). However, the tensor is very sparse because the number of tagged items is smaller than the amount of all items. The previous research do not consider the previous behaviors of users and items. To mitigate the problems, in this paper, the item-based collaborative filtering scheme is used to build an extended data. We also apply the probabilistic ranking algorithm considering the user and item profiles to improve the recommendation performance. The proposed method is evaluated based on Movielens dataset, and the results show that our approach improves the performance compared to other methods.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.389-392
• /
• 2020

The growth in social media, blogs and restaurant listing directories have led to increasing customer reviews about restaurants, their quality of food items and services available on the internet. These user reviews offer a massive amount of valuable information that can be used for various decision-making purposes. Currently, most food recommendation sites provide recommendation scores about restaurants rather than food items of the restaurant and the provided recommendation scores may be biased since they are calculated only from user reviews listed only in their sites. Usually, people wants a reliable recommendation about foods, not restaurant. In this paper, we present a reliable Korean food items rating method; we first extract food items by applying NER technique to restaurant reviews collected from many Korean restaurant recommendation web sites, blogs and web data. Then, we apply lexicon-based sentiment analysis on collected user reviews and predict people's opinions as sentiment polarity scores (+1 for positive; -1 for negative; 0 for neutral). Finally, by taking average of all calculated polarity scores about a food item, we obtain a rating to individual menu items of the restaurant. The proposed food item rating is more reliable since it does not depend on reviews of only one site.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 추계학술대회
• /
• pp.602-609
• /
• 2007

Combining collaborative filtering with some other technique is most common in hybrid recommender systems. As many recommended items from collaborative filtering seem to be similar with respect to content, the collaborative-content hybrid system suffers in terms of quality recommendation and recommending new items as well. To alleviate such problem, we have developed a novel method that uses a diversity metric to select the dissimilar items among the recommended items from collaborative filtering, which together with the input when fed into content space let us improve and include new items in the recommendation. We present experimental results on movielens dataset that shows how our approach performs better than simple content-based system and naive hybrid system

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.752-770
• /
• 2019

The purpose of this study is to incorporate telemarketing processes to improve telemarketing performance. For this application, we have attempted to mix the model of machine learning to extract potential customers with personalisation techniques to derive recommended products from actual contact. Most of traditional recommendation systems were mainly in ways such as collaborative filtering, which predicts items with a high likelihood of future purchase, based on existing purchase transactions or preferences for products. But, under these systems, new users or items added to the system do not have sufficient information, and generally cause problems such as a cold start that can not obtain satisfactory recommendation items. Also, indiscriminate telemarketing attempts can backfire as they increase the dissatisfaction and fatigue of customers who do not want to be contacted. To this purpose, this study presented a multi-purpose hybrid recommendation algorithm to achieve two goals: to select customers with high possibility of contact, and to recommend products to selected customers. In addition, we used subscription data from telemarketing agency that handles insurance products to derive realistic applicability of the proposed recommendation system. Our proposed recommendation system would certainly solve the cold start and scarcity problem of existing recommendation algorithm by using contents information such as customer master information and telemarketing history. Also. the model could show excellent performance not only in terms of overall performance but also in terms of the recommendation success rate of the unpopular product.

• 디지털산업정보학회논문지
• /
• 제9권1호
• /
• pp.43-52
• /
• 2013

Pervasive computing and social network are good resources in recommendation method. Collaborative filtering is one of the most popular recommendation methods, but it has some limitations such as rating sparsity. Moreover, it does not consider social network in pervasive computing environment. We propose an effective proactive friend recommendation method using social network and contexts in pervasive computing environment. In collaborative filtering method, users need to rate sufficient number of items. However, many users don't rate items sufficiently, because the rating information must be manually input into system. We solve the rating sparsity problem in the collaboration filtering method by using contexts. Our method considers both a static and a dynamic friendship using contexts and social network. It makes more effective recommendation. This paper describes a new friend recommendation method and then presents a music friend scenario. Our work will help e-commerce recommendation system using collaborative filtering and friend recommendation applications in social network services.

• Asia pacific journal of information systems
• /
• 제20권1호
• /
• pp.81-99
• /
• 2010

Lately, in consumers' markets the number of new items is rapidly increasing at an overwhelming rate while consumers have limited access to information about those new products in making a sensible, well-informed purchase. Therefore, item providers and customers need a system which recommends right items to right customers. Also, whenever new items are released, for instance, the recommender system specializing in new items can help item providers locate and identify potential customers. Currently, new items are being added to an existing system without being specially noted to consumers, making it difficult for consumers to identify and evaluate new products introduced in the markets. Most of previous approaches for recommender systems have to rely on the usage history of customers. For new items, this content-based (CB) approach is simply not available for the system to recommend those new items to potential consumers. Although collaborative filtering (CF) approach is not directly applicable to solve the new item problem, it would be a good idea to use the basic principle of CF which identifies similar customers, i,e. neighbors, and recommend items to those customers who have liked the similar items in the past. This research aims to suggest a hybrid recommendation procedure based on the preference boundary of target customer. We suggest the hybrid recommendation procedure using the preference boundary in the feature space for recommending new items only. The basic principle is that if a new item belongs within the preference boundary of a target customer, then it is evaluated to be preferred by the customer. Customers' preferences and characteristics of items including new items are represented in a feature space, and the scope or boundary of the target customer's preference is extended to those of neighbors'. The new item recommendation procedure consists of three steps. The first step is analyzing the profile of items, which are represented as k-dimensional feature values. The second step is to determine the representative point of the target customer's preference boundary, the centroid, based on a personal information set. To determine the centroid of preference boundary of a target customer, three algorithms are developed in this research: one is using the centroid of a target customer only (TC), the other is using centroid of a (dummy) big target customer that is composed of a target customer and his/her neighbors (BC), and another is using centroids of a target customer and his/her neighbors (NC). The third step is to determine the range of the preference boundary, the radius. The suggested algorithm Is using the average distance (AD) between the centroid and all purchased items. We test whether the CF-based approach to determine the centroid of the preference boundary improves the recommendation quality or not. For this purpose, we develop two hybrid algorithms, BC and NC, which use neighbors when deciding centroid of the preference boundary. To test the validity of hybrid algorithms, BC and NC, we developed CB-algorithm, TC, which uses target customers only. We measured effectiveness scores of suggested algorithms and compared them through a series of experiments with a set of real mobile image transaction data. We spilt the period between 1st June 2004 and 31st July and the period between 1st August and 31st August 2004 as a training set and a test set, respectively. The training set Is used to make the preference boundary, and the test set is used to evaluate the performance of the suggested hybrid recommendation procedure. The main aim of this research Is to compare the hybrid recommendation algorithm with the CB algorithm. To evaluate the performance of each algorithm, we compare the purchased new item list in test period with the recommended item list which is recommended by suggested algorithms. So we employ the evaluation metric to hit the ratio for evaluating our algorithms. The hit ratio is defined as the ratio of the hit set size to the recommended set size. The hit set size means the number of success of recommendations in our experiment, and the test set size means the number of purchased items during the test period. Experimental test result shows the hit ratio of BC and NC is bigger than that of TC. This means using neighbors Is more effective to recommend new items. That is hybrid algorithm using CF is more effective when recommending to consumers new items than the algorithm using only CB. The reason of the smaller hit ratio of BC than that of NC is that BC is defined as a dummy or virtual customer who purchased all items of target customers' and neighbors'. That is centroid of BC often shifts from that of TC, so it tends to reflect skewed characters of target customer. So the recommendation algorithm using NC shows the best hit ratio, because NC has sufficient information about target customers and their neighbors without damaging the information about the target customers.