• 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.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.69-86
• /
• 2021

As artificial intelligence technology advances, personalized recommendation systems using big data have attracted huge attention. In the case of beauty products, product preferences are clearly divided depending on customers' skin types and sensitivity along with individual tastes, so it is necessary to provide customized recommendation services based on accumulated customer data. Therefore, by employing deep learning methods, this study proposes a neural network-based recommendation model utilizing both product search history and context information such as gender, skin types and skin worries of customers. The results show that our model with context information outperforms collaborative filtering-based recommender system models using customer search history.

• Information Systems Review
• /
• v.23 no.3
• /
• pp.77-96
• /
• 2021

This research investigates the pivotal role of AI-enabled technologies in vitalizing the local economy. Collaborating with a leading search engine company, we examine the direct and indirect of an AI-based location search service on the success of sampled 7,035 local restaurants in Gangnam area in Seoul. We find that increased use of AI-enabled search and recommendation services significantly improved the selections of previously less-discovered or less-popular restaurants by users, and it also enhanced the stores' overall conversion rates. The main research findings have contributions to extant literature in theorizing the value of AI applications in local economy and have managerial implications for search businesses and local stores by recommending strategic use of AI applications in their businesses that are effective in highly competitive markets.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.108-117
• /
• 2024

The selection and recommendation of a suitable job applicant from the pool of thousands of applications are often daunting jobs for an employer. The recommendation and selection process significantly increases the workload of the concerned department of an employer. Thus, Resume Classification System using the Natural Language Processing (NLP) and Machine Learning (ML) techniques could automate this tedious process and ease the job of an employer. Moreover, the automation of this process can significantly expedite and transparent the applicants' selection process with mere human involvement. Nevertheless, various Machine Learning approaches have been proposed to develop Resume Classification Systems. However, this study presents an automated NLP and ML-based system that classifies the Resumes according to job categories with performance guarantees. This study employs various ML algorithms and NLP techniques to measure the accuracy of Resume Classification Systems and proposes a solution with better accuracy and reliability in different settings. To demonstrate the significance of NLP & ML techniques for processing & classification of Resumes, the extracted features were tested on nine machine learning models Support Vector Machine - SVM (Linear, SGD, SVC & NuSVC), Naïve Bayes (Bernoulli, Multinomial & Gaussian), K-Nearest Neighbor (KNN) and Logistic Regression (LR). The Term-Frequency Inverse Document (TF-IDF) feature representation scheme proven suitable for Resume Classification Task. The developed models were evaluated using F-Score_M, Recall_M, Precission_M, and overall Accuracy. The experimental results indicate that using the One-Vs-Rest-Classification strategy for this multi-class Resume Classification task, the SVM class of Machine Learning algorithms performed better on the study dataset with over 96% overall accuracy. The promising results suggest that NLP & ML techniques employed in this study could be used for the Resume Classification task.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.8
• /
• pp.367-373
• /
• 2024

The growth of mobile devices and network infrastructure has brought significant changes to the music industry. Online streaming services has allowed music consumption without constraints of time and space, leading to increased consumer engagement in music creation and sharing activities, resulting in a vast accumulation of music data. In this study, we define metadata as "song sentences" by using a user's playlist. To calculate similarity, we embedded them into a high-dimensional vector space using skip-gram with negative sampling algorithm. Performance eva luation results indicated that the recommended music algorithm, utilizing singers, genres, composers, lyricists, arrangers, eras, seasons, emotions, and tag lists, exhibited the highest performance. Unlike conventional recommendation methods based on users' behavioral data, our approach relies on the inherent information of the tracks themselves, potentially addressing the cold start problem and minimizing filter bubble phenomena, thus providing a more convenient music listening experience.

• Asia pacific journal of information systems
• /
• v.19 no.3
• /
• pp.51-67
• /
• 2009

Developing an agile recommender system for nomadic users has been regarded as a promising application in mobile and ubiquitous settings. To increase the quality of personalized recommendation in terms of accuracy and elapsed time, estimating future context of the user in a correct way is highly crucial. Traditionally, time series analysis and Makovian process have been adopted for such forecasting. However, these methods are not adequate in predicting context data, only because most of context data are represented as nominal scale. To resolve these limitations, the alignment-prediction algorithm has been suggested for context prediction, especially for future context from the low-level context. Recently, an ontological approach has been proposed for guided context prediction without context history. However, due to variety of context information, acquiring sufficient context prediction knowledge a priori is not easy in most of service domains. Hence, the purpose of this paper is to propose a novel context prediction methodology, which does not require a priori knowledge, and to increase accuracy and decrease elapsed time for service response. To do so, we have newly developed pattern-based context prediction approach. First of ail, a set of individual rules is derived from each context attribute using context history. Then a pattern consisted of results from reasoning individual rules, is developed for pattern learning. If at least one context property matches, say R, then regard the pattern as right. If the pattern is new, add right pattern, set the value of mismatched properties = 0, freq = 1 and w(R, 1). Otherwise, increase the frequency of the matched right pattern by 1 and then set w(R,freq). After finishing training, if the frequency is greater than a threshold value, then save the right pattern in knowledge base. On the other hand, if at least one context property matches, say W, then regard the pattern as wrong. If the pattern is new, modify the result into wrong answer, add right pattern, and set frequency to 1 and w(W, 1). Or, increase the matched wrong pattern's frequency by 1 and then set w(W, freq). After finishing training, if the frequency value is greater than a threshold level, then save the wrong pattern on the knowledge basis. Then, context prediction is performed with combinatorial rules as follows: first, identify current context. Second, find matched patterns from right patterns. If there is no pattern matched, then find a matching pattern from wrong patterns. If a matching pattern is not found, then choose one context property whose predictability is higher than that of any other properties. To show the feasibility of the methodology proposed in this paper, we collected actual context history from the travelers who had visited the largest amusement park in Korea. As a result, 400 context records were collected in 2009. Then we randomly selected 70% of the records as training data. The rest were selected as testing data. To examine the performance of the methodology, prediction accuracy and elapsed time were chosen as measures. We compared the performance with case-based reasoning and voting methods. Through a simulation test, we conclude that our methodology is clearly better than CBR and voting methods in terms of accuracy and elapsed time. This shows that the methodology is relatively valid and scalable. As a second round of the experiment, we compared a full model to a partial model. A full model indicates that right and wrong patterns are used for reasoning the future context. On the other hand, a partial model means that the reasoning is performed only with right patterns, which is generally adopted in the legacy alignment-prediction method. It turned out that a full model is better than a partial model in terms of the accuracy while partial model is better when considering elapsed time. As a last experiment, we took into our consideration potential privacy problems that might arise among the users. To mediate such concern, we excluded such context properties as date of tour and user profiles such as gender and age. The outcome shows that preserving privacy is endurable. Contributions of this paper are as follows: First, academically, we have improved sequential matching methods to predict accuracy and service time by considering individual rules of each context property and learning from wrong patterns. Second, the proposed method is found to be quite effective for privacy preserving applications, which are frequently required by B2C context-aware services; the privacy preserving system applying the proposed method successfully can also decrease elapsed time. Hence, the method is very practical in establishing privacy preserving context-aware services. Our future research issues taking into account some limitations in this paper can be summarized as follows. First, user acceptance or usability will be tested with actual users in order to prove the value of the prototype system. Second, we will apply the proposed method to more general application domains as this paper focused on tourism in amusement park.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.195-211
• /
• 2010

An exhibition is defined as market events for specific duration to present exhibitors' main product range to either business or private visitors, and it also plays a key role as effective marketing channels. Especially, as the effect of the opinions of the visitors after the exhibition impacts directly on sales or the image of companies, exhibition organizers must consider various needs of visitors. To meet needs of visitors, ubiquitous technologies have been applied in some exhibitions. However, despite of the development of the ubiquitous technologies, their services cannot always reflect visitors' preferences as they only generate information when visitors request. As a result, they have reached their limit to meet needs of visitors, which consequently might lead them to loss of marketing opportunity. Recommendation systems can be the right type to overcome these limitations. They can recommend the booths to coincide with visitors' preferences, so that they help visitors who are in difficulty for choices in exhibition environment. One of the most successful and widely used technologies for building recommender systems is called Collaborative Filtering. Traditional recommender systems, however, only use neighbors' evaluations or behaviors for a personalized prediction. Therefore, they can not reflect visitors' dynamic preference, and also lack of accuracy in exhibition environment. Although there is much useful information to infer visitors' preference in ubiquitous environment (e.g., visitors' current location, booth visit path, and so on), they use only limited information for recommendation. In this study, we propose a booth recommendation methodology using Sequential Association Rule which considers the sequence of visiting. Recent studies of Sequential Association Rule use the constraints to improve the performance. However, since traditional Sequential Association Rule considers the whole rules to recommendation, they have a scalability problem when they are adapted to a large exhibition scale. To solve this problem, our methodology composes the confidence database before recommendation process. To compose the confidence database, we first search preceding rules which have the frequency above threshold. Next, we compute the confidences of each preceding rules to each booth which is not contained in preceding rules. Therefore, the confidence database has two kinds of information which are preceding rules and their confidence to each booth. In recommendation process, we just generate preceding rules of the target visitors based on the records of the visits, and recommend booths according to the confidence database. Throughout these steps, we expect reduction of time spent on recommendation process. To evaluate proposed methodology, we use real booth visit records which are collected by RFID technology in IT exhibition. Booth visit records also contain the visit sequence of each visitor. We compare the performance of proposed methodology with traditional Collaborative Filtering system. As a result, our proposed methodology generally shows higher performance than traditional Collaborative Filtering. We can also see some features of it in experimental results. First, it shows the highest performance at one booth recommendation. It detects preceding rules with some portions of visitors. Therefore, if there is a visitor who moved with very a different pattern compared to the whole visitors, it cannot give a correct recommendation for him/her even though we increase the number of recommendation. Trained by the whole visitors, it cannot correctly give recommendation to visitors who have a unique path. Second, the performance of general recommendation systems increase as time expands. However, our methodology shows higher performance with limited information like one or two time periods. Therefore, not only can it recommend even if there is not much information of the target visitors' booth visit records, but also it uses only small amount of information in recommendation process. We expect that it can give real?time recommendations in exhibition environment. Overall, our methodology shows higher performance ability than traditional Collaborative Filtering systems, we expect it could be applied in booth recommendation system to satisfy visitors in exhibition environment.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• Asia pacific journal of information systems
• /
• v.20 no.1
• /
• 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.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.311-328
• /
• 2022

Because of the spread of smartphones due to the development of information and communication technology, online shopping mall services can be used on computers and mobile devices. As a result, the number of users using the online shopping mall service increases rapidly, and the types of products traded are also growing. Therefore, to maximize profits, companies need to provide information that may interest users. To this end, the recommendation system presents necessary information or products to the user based on the user's past behavioral data or behavioral purchase records. Representative overseas companies that currently provide recommendation services include Netflix, Amazon, and YouTube. These companies support users' purchase decisions by recommending products to users using ratings, purchase records, and clickstream data that users give to the items. In addition, users refer to the ratings left by other users about the product before buying a product. Most users tend to provide ratings only to products they are satisfied with, and the higher the rating, the higher the purchase intention. And recently, e-commerce sites have provided users with the ability to vote on whether product reviews are helpful. Through this, the user makes a purchase decision by referring to reviews and ratings of products judged to be beneficial. Therefore, in this study, the correlation between the product rating and the helpful information of the review is identified. The valuable data of the evaluation is reflected in the recommendation system to check the recommendation performance. In addition, we want to compare the results of skipping all the ratings in the traditional collaborative filtering technique with the recommended performance results that reflect only the 4 and 5 ratings. For this purpose, electronic product data collected from Amazon was used in this study, and the experimental results confirmed a correlation between ratings and review usefulness information. In addition, as a result of comparing the recommendation performance by reflecting all the ratings and only the 4 and 5 points in the recommendation system, the recommendation performance of remembering only the 4 and 5 points in the recommendation system was higher. In addition, as a result of reflecting review usefulness information in the recommendation system, it was confirmed that the more valuable the review, the higher the recommendation performance. Therefore, these experimental results are expected to improve the performance of personalized recommendation services in the future and provide implications for e-commerce sites.