Development Of Recommender Systems Research Articles

Seminar and Training Programs Recommender System for Faculty Members of Higher Education Institution

This study aims to develop a personalized Recommender System that helps to address the problems encountered by the faculty members of Higher Education Institutions in the selection of Seminar and Training Programs (STP). The researcher used the Descriptive Developmental Method of research to gather information relevant to the current problems and challenges encountered and used these to develop software that addresses the identified challenges. For the development of the software, the researcher adopted a step-wise approach defined in the Incremental Developmental Model. The level of acceptance of the developed system was evaluated by 24 faculty respondents. The level of acceptance of the developed system was classified into functionality, reliability, and usability and the study garnered an evaluation score of 4.65, 4.67, and 4.67 respectively. The overall interpretation of the results of the evaluation is Highly Acceptable. The study created a system that provides seminars and training program recommendations. The developed recommender system was rated Highly Acceptable, respondents were very satisfied with the features of the system and agreed that it was functional, reliable, and usable.

GotFunding: A grant recommendation system based on scientific articles

AbstractObtaining funding is an important part of becoming a successful scientist. Junior faculty spend a great deal of time finding the right agencies and programs that best match their research profile. But what are the factors that influence the best publication–grant matching? Some universities might employ pre‐award personnel to understand these factors, but not all institutions can afford to hire them. Historical records of publications funded by grants can help us understand the matching process and also help us develop recommendation systems to automate it. In this work, we present GotFunding (Grant recOmmendaTion based on past FUNDING), a recommendation system trained on National Institutes of Healthʼs (NIH) grant–publication records. Our system achieves a high performance (NDCG@1 = 0.945) by casting the problem as learning to rank. By analyzing the features that make predictions effective, our results show that the ranking considers most important (a) the year difference between publication and grant, (b) the amount of information provided in the publication, and (c) the relevance of the publication to the grant. We further discuss the implications and future improvements to this work.

Regression analysis of student academic performance using deep learning

Educational data mining helps the educational institutions to perform effectively and efficiently by exploiting the data related to all its stakeholders. It can help the at-risk students, develop recommendation systems and alert the students at different levels. It is beneficial to the students, educators and authorities as a whole. Deep learning has gained momentum in various domains especially image processing with a large dataset. We devise a regression model for analyzing the academic performance of the students using deep learning. We have applied regression using deep learning and linear regression on the dataset. For such models with smaller datasets, to tackle the issue of overfitting is critical. Hence, the parameters can be tuned to deal with such issues. The deep learning model records a mean absolute score (mae) of 1.61 and loss 4.7 with the value of k = 3. While the linear regression model yields a loss of 6.7 and mae score of 1.97. The deep learning model outperforms the linear regression model. The model may be successfully extended to other programmes to mine and predict the performance of the learners.

Integrating Community Context Information Into a Reliably Weighted Collaborative Filtering System Using Soft Ratings

In this paper, we aim at developing a new collaborative filtering recommender system using soft ratings, which is capable of dealing with both imperfect information about user preferences and the sparsity problem. On the one hand, Dempster–Shafer theory is employed for handling the imperfect information due to its advantage in providing not only a flexible framework for modeling uncertain, imprecise, and incomplete information, but also powerful operations for fusion of information from multiple sources. On the other hand, in dealing with the sparsity problem, community context information that is extracted from the social network containing all users is used for predicting unprovided ratings. As predicted ratings are not a hundred percent accurate, while the provided ratings are actually evaluated by users, we also develop a new method for calculating user–user similarities, in which provided ratings are considered to be more significant than predicted ones. In the experiments, the developed recommender system is tested on two different data sets; and the experiment results indicate that this system is more effective than CoFiDS, a typical recommender system offering soft ratings.

A driver behavior assessment and recommendation system for connected vehicles to produce safer driving environments through a “follow the leader” approach

As part of the emerging world of intelligent transportation, there is considerable interest in developing connected vehicles that are more capable of identifying and guiding individual drivers’ behavior than collecting mileage as a moving cart. The two goals of this study are (a) to build a conceptual framework for driver assessment and (b) develop recommendation systems to evaluate individual driving performance and guide driver behaviors, thus improving the network traffic conditions and individuals’ perceived safety. A safety score is defined relatively by comparing a driver’s individual pattern to a standard “safe driver” pattern. To elaborate, the proposed system adopts advanced data mining techniques to extract, identify, characterize, and display driving behavior patterns. The scoring system provides a basis of assessing individual drivers, who are then recommended to mimic a nearby “safe” driver in a connected environment. To evaluate and implement the proposed conceptual framework, an anonymous trajectory dataset collected from Pittsburgh urban area is applied to build the scoring system, which is then integrated within a virtually simulated environment. The results show that the proposed behavior assessment and recommendation system framework improves the overall performance of a connected traffic system beyond those attained through baseline connectivity principles.

Health App Recommendation System using Ensemble Multimodel Deep Learning

Nowadays, mobile devices and apps are meant to fulfill the needs of various people in society. But, mobile app Stores are facing major challenges in recommending proper apps for users. Recommending mobile apps for users according to personal preference and various mobile device limitations is therefore important. In this scenario, there is a huge need for developing recommender systems (RS) for the user’s community in enabling critical mobile apps such as Health based Apps. Recommendation Systems perform an extensive survey on the collection of user reviews, preferences and opinions to discover recommendations of suitable applications to the users' community. In this paper, we have designed an aspect-based recommendation framework by performing three tasks: such as identifying the mentions associated with item aspects in user reviews, extracting the sentiment related opinions using Latent Semantic Analysis of such aspects in the reviews, and perform the opinion mining from all of the aspects to generate enhanced recommendations with Ensemble Multimodel Deep Learning (EMDL). EMDL comprises of two state-of- the-art classifiers such as Deep Neural Networks (DNN) and Long Short Term Memory (LSTM). In contrast to the prior work, we conducted a series of experiments with several state-of-art deep learning models to extract useful recommendations. The achieved results show that classification with outperforms in all the aspects based on various evaluation metrics when compared to the rest of the models.

Multi-Objective Evolutionary Programming for Developing Recommender Systems based on Collaborative Filtering

In the era of internet, several online platforms offer many items to users. Users could spend a lot of time to find (or not) some items they are interested, sometimes, they will probably not find the desired items. An effective strategy to overcome this problem is a recommender system, one of the most popular applications of machine learning. Recommender systems select most appropriate items to an specific user based on previous information between items and users, and they are developed using diffeent approaches. One of the most successful approach for developing recommender systems is collaborative filtering, which can filter out items that a user might like based on reactions of users with similar profiles. Often, traditional recommender systems only consider precision as evaluation metric of performance, however, others metrics (like recall, diversity, novelty, etc) are also important. Unfortunately, some metrics are conflicting, e.g., precision impacts negatively on other metrics. This paper presents a multi-objective evolutionary programming method for developing a recommender system, which is based on a new collaborative filtering technique, while maximizes the recall for a given precision, The new collaborative filtering technique uses three components for recommending an item to a user: 1) clustering of users; 2) a previous memory-based prediction; and 3) five decimal parameters (threshold average clustering, threshold penalty, threshold incentive, weight attached to average clustering and weight attached to Pearson correlation). The multiobjective evolutionary programming optimizes the clustering of users and the five decimal parameters, while, it searches maximizes both similarity precision and recall objectives. A comparison between the proposed method and a previous nonevolutionary method shows that the proposed method improves precision and recall metric on a benchmark database.

Integrating selection-based aspect sentiment and preference knowledge for social recommender systems

PurposeRecommender system approaches such as collaborative and content-based filtering rely on user ratings and product descriptions to recommend products. More recently, recommender system research has focussed on exploiting knowledge from user-generated content such as product reviews to enhance recommendation performance. The purpose of this paper is to show that the performance of a recommender system can be enhanced by integrating explicit knowledge extracted from product reviews with implicit knowledge extracted from analysis of consumer’s purchase behaviour.Design/methodology/approachThe authors introduce a sentiment and preference-guided strategy for product recommendation by integrating not only explicit, user-generated and sentiment-rich content but also implicit knowledge gleaned from users’ product purchase preferences. Integration of both of these knowledge sources helps to model sentiment over a set of product aspects. The authors show how established dimensionality reduction and feature weighting approaches from text classification can be adopted to weight and select an optimal subset of aspects for recommendation tasks. The authors compare the proposed approach against several baseline methods as well as the state-of-the-art better method, which recommends products that are superior to a query product.FindingsEvaluation results from seven different product categories show that aspect weighting and selection significantly improves state-of-the-art recommendation approaches.Research limitations/implicationsThe proposed approach recommends products by analysing user sentiment on product aspects. Therefore, the proposed approach can be used to develop recommender systems that can explain to users why a product is recommended. This is achieved by presenting an analysis of sentiment distribution over individual aspects that describe a given product.Originality/valueThis paper describes a novel approach to integrate consumer purchase behaviour analysis and aspect-level sentiment analysis to enhance recommendation. In particular, the authors introduce the idea of aspect weighting and selection to help users identify better products. Furthermore, the authors demonstrate the practical benefits of this approach on a variety of product categories and compare the approach with the current state-of-the-art approaches.

An Experimental Study on the Swaying Effect of Web-Personalization

The multi-dimensionality of online word-of-mouth not only provides rich attribute-level information but also influences the attribute preference construction of the online consumer. Though prior research affirms that consumer reviews impact the attribute preference assessment of a consumer in a non-personalized single-product environment, in a personalized, multiple alternative environment, consumers' behavior could be completely different and requires separate attention. Building on the information processing approach and constructive preference perspective, our research analyzes how personalization influences this swaying effect, i.e., the influence of personalization on the attribute preference of a consumer. We conducted a multi-group experiment with four different types of personalization - non-personalized information (no personalization), self-referent information, relevant information, and both self-referent and relevant information. Our results show evidence of a swaying effect of personalization on consumers' attribute preference for products. We found that users, when exposed to different types of personalization, experience different levels of the swaying effect on their attribute preferences of the product. This study contributes significantly to the current discourse on the setbacks of web personalization and also informs practicing managers on how to develop recommender system strategies.

Enhancing Traditional Recommender Systems via Social Communities

Collaborative Filtering (CF) has become the most popular approach for developing Recommender Systems in diverse business applications. Unfortunately, problems such as the cold-start problem (i.e., new users or items enter the system and for those no previous preference information is available) and the gray sheep problem (i.e., cases in which a user profile does not match any other profile in the user community) are widely recognized for hindering recommendation effectiveness of traditional CF methods. To alleviate such problems, substantial research has focused on enhancing CF with social information about users (e.g., social relationships and communities). However, despite the crescent interest in social-based approaches, researches and practitioners face the challenge of developing their own Recommender System architecture for appropriately combining social and collaborative filtering methods to improve recommendation results. In this paper, we address this issue by introducing a flexible architecture to support researchers and practitioners in the task of designing real-world Recommender Systems that exploit social network data. We focus on detailing our proposed architecture modules and their interplay, potential algorithms for extracting and combining relevant social information, and candidate technologies for handling diverse and massive data volumes. Additionally, we provide an empirical analysis demonstrating the effectiveness of the proposed architecture on alleviating the cold-start problem over a concrete experimental case.

A qualitative attraction ranking model for personalized recommendations

定性旅游胜地个性化推荐模型摘要研究目的本研究主要探索如何建立个性化旅游胜地推荐模型。本研究通过分析旅游兴趣相似的游客意见和游客偏好选择, 建立一种更加准确推荐游客需要的旅游胜地方法。研究设计/方法/途径为了达到研究目的, 本研究建立了一种个性化推荐旅游胜地的信息系统。其系统通过分析每个游客的旅游偏好来建设一种定性旅游胜地排名模型。这种新型模型主要通过结合以下两种分析算法：（1）K平均聚类算法（K-means clustering）（2）层次分析法（AHP）。研究结果本研究建立的推荐信息系统经过了准确率和拓展性的测评。实验结果表明这种排名模型的准确率并不受旅游胜地多少和游客样本大小的影响。此外, 这种排名模型也具有拓展性, 因为算法时间并不受游客样本大小的影响。最后, 研究实验表明此排名模型客户体验性达到合格满意要求。研究理论限制/意义本研究的主要理论意义在于其结合了K平均聚类算法和层次分析法, 并建立了一种新型定性排名模型, 这种排名模型个性化地推荐更高质量的旅游胜地给游客。然而, 这种推荐信息系统有一些局限性。第一, 新旅游胜地的信息需要手动输入。第二, 整个系统的处理时间决定于网络带宽和延迟状况。研究实践意义本研究的实践意义在于其建立了一种准确和具有拓展性的新型旅游胜地推荐模型。这种模型的潜在价值将有利于旅游机构提供定制化旅游套餐和帮助游客制定旅游计划。此外, 这种模型还可以结合旅游路线计划系统以制定更加使游客满意的旅游行程。研究原创性/价值本研究推荐了一种基于定性旅游胜地排名模型的个性化旅游推荐模型。这种新型的排名模型结合K平均聚类算法和层次分析法, 实验证明这种模型更具准确性和拓展性。

전자 저널 구독 정보 및 웹 이용 로그를 활용한 참고문헌 기반 저널 추천 기법

전자 학술 정보 유통의 확대에 따라 날로 증가되는 학술 콘텐츠 서비스 수요에 부응하기 위하여 보다 효과적인 학술 콘텐츠 추천 시스템 개발이 요구된다. 학술 콘텐츠 추천 시스템은 정보 소비자의 과거 이용 내역을 기반으로 각 소비자 선호(preference)에 맞는 학술 콘텐츠를 제공함으로써 콘텐츠 이용성을 보다 효과적으로 향상 시킬 수 있다. 본 논문에서는 특정 기관에 소속된 사용자의 선호에 더욱 부합하는 학술 콘텐츠를 제공하기 위하여 기관의 전자 저널 구독 정보 및 웹 이용 로그를 활용한 저널 추천 기법을 제안한다. 제안하는 추천 기법에서는 기관 사용자의 저널 선호도를 효과적으로 예측하기 위하여 기관 유사도(Institution similarity), 그리고 참고문헌의 인용 관계 데이터를 기반으로 저널 유사도(Journal similarity) 및 저널 중요도(Journal importance)를 산출하여 최종적으로 기관 맞춤형 저널 추천 항목을 구성하게 된다. 또한, 제안하는 추천기법이 적용된 기관 맞춤형 저널 추천 시스템 프로토타입을 개발한다. 개발된 저널 추천 시스템은 각 기관의 저널 선호도 예측을 위하여 활용되는 웹 이용로그를 효과적으로 수집하고 이를 추천 기법에 활용하기 용이한 데이터로 가공 처리 하여 별도의 데이터베이스에 저장하여 추천 기법의 저널 선호도 예측을 위한 기반 데이터로 활용한다. 마지막으로 우리는 기존 추천 기법들과의 비교 성능 평가를 통해 제안 기법의 차별성과 우수성을 보인다. With the exploration of digital academic information, it is certainly required to develop more effective academic contents recommender system in order to accommodate increasing needs for accessing more personalized academic contents. Considering historical usage data, the academic content recommender system recommends personalized academic contents which corresponds with each user's preference. So, the academic content recommender system effectively increases not only the accessibility but also usability of digital academic contents. In this paper, we propose the new journal recommendation technique based on information of journal subscription and web usage logs in order to properly recommend more personalized academic contents. Our proposed recommendation method predicts user's preference with the institution similarity, the journal similarity and journal importance based on citation relationship data of references and finally compose institute-oriented recommendations. Also, we develop a recommender system prototype. Our developed recommender system efficiently collects usage logs from distributed web sites and processes collected data which are proper to be used in proposed recommender technique. We conduct compare performance analysis between existing recommender techniques. Through the performance analysis, we know that our proposed technique is superior to existing recommender methods.

A Review on Current Recommendation Systems

In recent years, E-commerce, web service and web information system have been used explosively. Massive explosion of the world-wide-web and the emergence of ecommerce have encouraged designers to develop recommendation systems. Web users demonstrate a variety of navigational patterns by clicking series of web pages. These patterns can be understood by mining user logs using WUM. One of the widely used applications of Web Usage Mining is Online Recommendation and prediction. Generally, all the recommendation systems follow a framework for generating efficient recommendations. Various recommendation systems use different approaches based on the sources of information they utilize. The accessible sources are user information (demographics), the product information (keywords, genres) and the user-item ratings. This paper gives introductive information about recommendation system, their techniques, and algorithms and also describes some existing works.

Selection criteria for text mining approaches

Text mining techniques include categorization of text, summarization, topic detection, concept extraction, search and retrieval, document clustering, etc. Each of these techniques can be used in finding some non-trivial information from a collection of documents. Text mining can also be employed to detect a document’s main topic/theme which is useful in creating taxonomy from the document collection. Areas of applications for text mining include publishing, media, telecommunications, marketing, research, healthcare, medicine, etc. Text mining has also been applied on many applications on the World Wide Web for developing recommendation systems. We propose here a set of criteria to evaluate the effectiveness of text mining techniques in an attempt to facilitate the selection of appropriate technique.

Smart collaboration framework for managing chronic disease using recommender system

E-Healthcare services show promising solutions to reduce patients’ life risk with improving the provided services along with being cost effective. This paper presents Chronic Disease Recommender System that assists patients to monitor and control their cases through suggesting medical advices and diagnosis. For the system to be accurate, which is vital in such application, it needs to work with high-dimensional data. This work proposed Integrated Collaborative Filtering framework that reduces the complexity and improves the response time of high-dimensional data to develop recommender system. The paper concluded with presenting and discussing real case study with real medical data on providing medical advices for diabetes.

Implicit feedback techniques on recommender systems applied to electronic books

The goal of this research is to define and capture a series of parameters that allowed us to perform a comparative analysis and find correlations between explicit and implicit feedback on recommender systems. Most of these systems require explicit actions from the users, such as rating, and commenting. In the context of electronic books this interaction may alter the patterns of reading and understanding of the users, as they are asked to stop reading and rate the content. By simulating the behavior of an electronic book reader we have improved the feedback process, by implicitly capturing, measuring, and classifying the information needed to discover user interests. In these times of information overload, we can now develop recommender systems that are mostly based on the user’s behavior, by relying on the obtained results.

Recommender System to Research Students’ Study Efficiency

The Recommender System to Research Students’ Study Efficiency (Recommender System hereafter) developed by these authors determines a student's learning productivity based on that same student's physiological, psychological and behavioral/movement parameters. It then generates thousands of alternative learning productivity recommendations based on the compiled Maslow's Pyramid Tables and selects out the most rational of these for the student's specific situation. The Recommender System provides a student with a real-time assessment of his/her own learning productivity and emotional state. This article presents the Recommender System, a case study and a scenario used to test and validate the developed Recommender System and its composite parts to demonstrate its validity, efficiency and usefulness

Improved Accuracy of PSO and DE using Normalization: an Application to Stock Price Prediction

Data Mining is being actively applied to stock market since 1980s. It has been used to predict stock prices, stock indexes, for portfolio management, trend detection and for developing recommender systems. The various algorithms which have been used for the same include ANN, SVM, ARIMA, GARCH etc. Different hybrid models have been developed by combining these algorithms with other algorithms like roughest, fuzzy logic, GA, PSO, DE, ACO etc. to improve the efficiency. This paper proposes DE-SVM model (Differential Evolution- Support vector Machine) for stock price prediction. DE has been used to select best free parameters combination for SVM to improve results. The paper also compares the results of prediction with the outputs of SVM alone and PSO-SVM model (Particle Swarm Optimization). The effect of normalization of data on the accuracy of prediction has also been studied.

Recommender System for Real Estate Management

The analysis of information, the expert and decision support systems used in real estate management that were developed by researchers from various countries assisted the authors in creating their own Recommender System for Real Estate Management (RSREM). The database of real estate management was developed providing a comprehensive assessment of alternative versions from the economic, technical, technological, infrastructure, qualitative, technological, legislative and other perspectives. Based on the above complex databases, the developed Recommender System for Real Estate Management enables the user to analyse alternatives quantitatively (i.e. a system and subsystems of criteria, units of measure, values and weights) and conceptually (i.e. the text, formula, schemes, graphs, diagrams and videotapes) and provides recommendations.

A probabilistic approach to semantic collaborative filtering using world knowledge

Collaborative filtering, which is a popular approach for developing recommendation systems, exploits the exact match of items that users have accessed. If the users access different items, they are considered as unlike-minded users even though they may actually be semantically like-minded. To solve this problem, we propose a semantic collaborative filtering model that represents the semantics of users’ preferences and items with their corresponding concepts. In this work, we extend the Bayesian belief network (BBN)-based model because it provides a clear formalism for representing users’ preferences and items with concepts. Because the conventional BBN-based model regards the index terms derived from items as concepts, it does not exploit domain knowledge. We have therefore extended this conventional model to exploit concepts derived from domain knowledge. A practical approach to exploiting domain knowledge is to use world knowledge such as the Open Directory Project web directory or the Wikipedia encyclopaedia. Through experiments, we show that our model outperforms other conventional collaborative filtering models while comparing the recommendation quality when using different world knowledge.