Hybrid Recommendation Technique Research Articles

Analysis and Prospect of Recommendation System on social media

Recommendation system works surprisingly well on providing interesting and informative contents to individual user by matching suitable information with target users, and it tremendously reduces the time users spend for searching relative contents while it is also cutting back the workload of content providers. There are two popular recommendation techniques: content-based and collaborative based filtering. The abilities of each technique is compared and analyzed, and how well they match the need of users on the social media platform. In addition, a typical form of hybrid recommendation that has the advantages of multiple techniques is also taken in the comparison. From the perspective of users in social media, each specific technique achieves some degree of success for the overall user satisfaction. Integrating techniques is a valuable attempt. This paper presents a look the origin and the development of recommender system in the past. The evolution of recommendation provides insight regarding what the future of recommender will become. The architecture of recommender system is also reviewed for understanding the way system performs. The key component inside the recommender architecture including matching, filtering, and objects utilized by technique which are critical factors in determination of prediction are examined. Different techniques used in filtering are analyzed for recognizing the advantages and the disadvantages for the purpose of social media. After all, the effectiveness of the hybrid recommendation technique on dealing with limitations of popular filtering is demonstrated.

Job Recommendation Systems: A Literature Review

This paper comparatively reviews the different recommendation models amidst the different classifier filtering techniques. Recommender systems have been adopted in other areas of life to provide custom-made solutions to netizen. The accuracy or weakness of a recommender system is based on the recommendation approach and filtering techniques adopted. Recommenders’ systems are developed to suit the needs and personal interests of the users. This paper review looks into previous and current recommender systems with a view of the different characteristics, advantages and disadvantages. This paper also undertakes a comparative review of hybrid recommendation techniques as regards to improving job recommendation systems.

A Ranking Recommendation Algorithm Based on Dynamic User Preference.

In recent years, hybrid recommendation techniques based on feature fusion have gained extensive attention in the field of list ranking. Most of them fuse linear and nonlinear models to simultaneously learn the linear and nonlinear features of entities and jointly fit user-item interactions. These methods are based on implicit feedback, which can reduce the difficulty of data collection and the time of data preprocessing, but will lead to the lack of entity interaction depth information due to the lack of user satisfaction. This is equivalent to artificially reducing the entity interaction features, limiting the overall performance of the model. To address this problem, we propose a two-stage recommendation model named A-DNR, short for Attention-based Deep Neural Ranking. In the first stage, user short-term preferences are modeled through an attention mechanism network. Then the user short-term preferences and user long-term preferences are fused into dynamic user preferences. In the second stage, the high-order and low-order feature interactions are modeled by a matrix factorization (MF) model and a multi-layer perceptron (MLP) model, respectively. Then, the features are fused through a fully connected layer, and the vectors are mapped to scores. Finally, a ranking list is output through the scores. Experiments on three real-world datasets (Movielens100K, Movielens1M and Yahoo Movies) show that our proposed model achieves significant improvements compared to existing methods.

Towards efficient navigation in digital libraries: Leveraging popularity, semantics and communities to recommend scholarly articles

• Our study proposes a novel algorithm, SPACE-R, which aims to improve the scalability and accuracy of large real-world academic recommendation systems. • This study incorporates the “quality” of papers by the construction of a Popularity Network, a derivative of the citation network, with importance given to author and journal impact. • The significance of a neighborhood network of a dynamic radius r has been demonstrated in the overall performance of the recommender system. • The judicious incorporation of a weighted sum of recency, quality, and semantic similarity as a personalization vector in the ranking process enhances the diversity of recommendations. • Community structure has been leveraged to get more topically similar papers as well as to reduce the search space, making the recommendation process scalable. The growing popularity of digital libraries as a medium for communicating scientific discoveries has made a large variety of research articles easily accessible. However, this constitutes a putative issue of information overloading with recommendation engines providing a compelling solution to the problem. Scientific Recommender Systems alleviate this problem by suggesting potential papers of interest to a user. For any researcher seeking developments in their field, it is important that the recommended papers are of high quality, recent and related to the field of interest, which has been largely overlooked in prior approaches. This study thus proposes a graph-based hybrid recommendation technique, SPACE-R , that amalgamates quality, semantic similarity and community structure of nodes in a citation network. The creation of a popularity network, a derivative of a citation network, in combination with a two-stage candidate selection process involving community detection and neighbourhood network identification, contributes to an improvement in the accuracy and scalability of the proposed model. The incorporation of semantic similarity achieves the necessary diversity in recommendations. Experimental evaluations on four large datasets against five baselines reveal that SPACE-R achieves an improvement of up to 45.53%, 56.76%, 49.39%, 46.84% and 78.18% in recall, precision, MRR, mAP, and response time, respectively.

A hybrid recommendation technique using topic embedding for rating prediction and to handle cold-start problem

Recommender systems aim to estimate item ratings and recommend items based on the users’ interests. The traditional recommender systems generally consider user–item rating information for rating prediction, but they suffer from various limitations, such as data sparsity, black-box recommendation, and cold-start problems. As a result, researchers have proposed amalgamating contextual information with rating data to provide effective recommendations. Although user-generated data in the form of reviews are a rich source of contextual information, they are rarely utilized in recommender algorithms. This study presents a hybrid recommendation technique, called RecTE, using rating data and topic embedding, which is an amalgamation of word embedding and topic modeling techniques. The novelty of RecTE lies in predicting item ratings using topic embeddings learned by incorporating local and global contextual information and integrating them with user-based collaborative filtering. RecTE is empirically evaluated over three real-world datasets – YelpNYC, YelpZip and TripAdvisor. This technique performs significantly better in comparison to nine baselines and five state-of-the-art recommendation techniques. On empirical analysis, we found that incorporating topic embedding in RecTE makes it capable of performing significantly better and handle cold-start problems effectively in comparison to the existing recommendation approaches.

Affinity Propagation-Based Hybrid Personalized Recommender System

A personalized recommender system is broadly accepted as a helpful tool to handle the information overload issue while recommending a related piece of information. This work proposes a hybrid personalized recommender system based on affinity propagation (AP), namely, APHPRS. Affinity propagation is a semisupervised machine learning algorithm used to cluster items based on similarities among them. In our approach, we first calculate the cluster quality and density and then combine their outputs to generate a new ranking score among clusters for the personalized recommendation. In the first phase, user preferences are collected and normalized as items rating matrix. This generated matrix is then clustered offline using affinity propagation and kept in a database for future recommendations. In the second phase, online recommendations are generated by applying the offline model. Negative Euclidian similarity and the quality of clusters are used together to select the best clusters for recommendations. The proposed APHPRS system alleviates problems such as sparsity and cold-start problems. The use of affinity propagation and the hybrid recommendation technique used in the proposed approach helps in improving results against sparsity. Experiments reveal that the proposed APHPRS performs better than most of the existing recommender systems.

Document Recommendations and Feedback Collection Analysis within the Slovenian Open-Access Infrastructure

This paper presents a hybrid document recommender system intended for use in digital libraries and institutional repositories that are part of the Slovenian Open Access Infrastructure. The recommender system provides recommendations of similar documents across different digital libraries and institutional repositories with the aim to connect researchers and improve collaboration efforts. The hybrid recommender system makes use of document processing techniques, document metadata, and the similarity ranking function BM25 to provide content-based recommendations as a primary method. It also uses collaborative-filtering methods as a secondary method in a cascade hybrid recommendation technique. We also provide a real-world data feedback collection analysis for our hybrid recommender system on an academic digital repository in order to be able to identify suitable time-frames for direct feedback collection during the year.

A Context-aware Approach for Adapting Scientific E-Learning Objects

E-learning has arisen as a promising solution to lifelong learning and job training. It changed the way people learn and gain knowledge. Moreover, it has been embedded in many information systems as user guides to help and support them in their workplaces. Yet, these guides have been designed in a one-size-fits-all fashion that serves generic learners irrespective of their individual contexts. The developers of Scientific Data Management Systems (SDMSs) provide all scientists with a textual guide regardless of their contexts such as learning styles and expertise levels. In this paper, we propose a proactive context-aware approach for recommending personalized scientific data management e-learning objects. The proposed approach improves the learning process of the scientific data management depending on the scientist profile and his or her environmental context. The proposed approach includes two phases. First, the approach semantically detects the scientist’s context. Secondly, a hybrid recommendation technique is introduced to provide the scientist with an adapted list of learning objects. To create a generic approach, the web service-based methodology is exploited to facilitate the integration with any SDMS.

Can I have more of these please?

PurposeDuring the literature review phase, the task of finding similar research papers can be a difficult proposition for researchers due to the procedural complexity of the task. Current systems and approaches help in finding similar papers for a given paper, even though researchers tend to additionally search using a set of papers. This paper aims to focus on conceptualizing and developing recommendation techniques for key literature review and manuscript preparatory tasks that are interconnected. In this paper, the user evaluation results of the task where seed basket-based discovery of papers is performed are presented.Design/methodology/approachA user evaluation study was conducted on a corpus of papers extracted from the ACM Digital Library. Participants in the study included 121 researchers who had experience in authoring research papers. Participants, split into students and staff groups, had to select one of the provided 43 topics and run the tasks offered by the developed assistive system. A questionnaire was provided at the end of each task for evaluating the task performance.FindingsThe results show that the student group evaluated the task more favourably than the staff group, even though the difference was statistically significant for only 5 of the 16 measures. The measures topical relevance, interdisciplinarity, familiarity and usefulness were found to be significant predictors for user satisfaction in this task. A majority of the participants, who explicitly stated the need for assistance in finding similar papers, were satisfied with the recommended papers in the study.Originality/valueThe current research helps in bridging the gap between novices and experts in terms of literature review skills. The hybrid recommendation technique evaluated in this study highlights the effectiveness of combining the results of different approaches in finding similar papers.

A Survey of Azure ML Recommender System

large amount of data in the websites today has made it difficult for the user to access the data which he wishes to view. Recommendation systems are tool or technique which helps user to find the most suitable products. So, the recommendation system plays very important role and helps user to get according to their need and interest. It was not so easy or straightforward to build a recommender but azure machine learning makes it very easy to build one as long as you have your data is ready. Major task of recommender system is to present recommendations to users. Hybrid Recommendation technique use multiple techniques together content based and collaborative filtering.

Hybrid Recommendation Technique Selection Center Donated Bags with Data Envelopment Analysis

The main purpose of this paper to present Natural Disasters problem case study Thailand flood 2554 To hybrid recommendation technique Selection center donated bags is deemed to be one of challenging problems that can be used to imply the management competency due to the fact that it is a difficult and complicated task in logistics supplier function. This article aims to introduce an approach to measuring the Shelters performance by using Data Evaluation Analysis. The DEA is a linear programming-based technique with less complication and exists an available method of simplex algorithms to solve the problem for measuring the efficiency of suppliers. The paper illustrates how to apply the DEA technique by using the data collected from donor bags person plant, which is making contact with 10 center donated bags to provide required for the Shelters plant. To evaluate the performance of the center donated bags, the procurement department employs input criteria of quality, and delivery. The results of the evaluation indicate that there are only center donated bags marked as relative efficient firms and the remaining 10 center donated bags are sorted as non-efficient firms. In addition, the results can be used to create negotiation strategies performance for send bags the Shelters from the inefficient center donated bags by using the value of reference time, weights. Specifically, the inefficient center donated bags will have to reduce the value of the input criteria by the proportion of reference weights in order that the inferior center donated bags could be attained to the benchmark points of relative efficiency.

On the integration of hybrid recommendation techniques into an agent-based transportation transactions management platform

Diverse recommendation techniques have been already proposed and encapsulated into several e-business applications, aiming to perform a more accurate evaluation of the existing information and accordingly augment the assistance provided to the users involved. This paper reports on the development and integration of a recommendation module in an agent-based transportation transactions management system. The module is built according to a novel hybrid recommendation technique, which combines the advantages of collaborative filtering and knowledge-based approaches. The proposed technique and supporting module assist customers in considering in detail alternative transportation transactions that satisfy their requests, as well as in evaluating completed transactions. The related services are invoked through a software agent that constructs the appropriate knowledge rules and performs a synthesis of the recommendation policy.

A hybrid recommendation technique based on product category attributes

Recommender systems are powerful tools that allow companies to present personalized offers to their customers and defined as a system which recommends an appropriate product or service after learning the customers’ preferences and desires. Extracting users’ preferences through their buying behavior and history of purchased products is the most important element of such systems. Due to users’ unlimited and unpredictable desires, identifying their preferences is very complicated process. In most researches, less attention has been paid to user’s preferences varieties in different product categories. This may decrease quality of recommended items. In this paper, we introduced a technique of recommendation in the context of online retail store which extracts user preferences in each product category separately and provides more personalized recommendations through employing product taxonomy, attributes of product categories, web usage mining and combination of two well-known filtering methods: collaborative and content-based filtering. Experimental results show that proposed technique improves quality, as compared to similar approaches.

An ontology-based approach for providing multimedia personalised recommendations

This paper provides a service-oriented solution that explores the ontology-based modelling of users and documents in order to provide users with personalised recommendations of resources. Alongside the adoption of semantic web technologies for ontology-based modelling, our approach aims at a better relevance for recommendations by adopting a hybrid recommendation technique, combining a collaborative filtering and a content-based approach. The collaborative filtering module adopts a Markov Decision Process (MDP) in order to predict the next concept which will be focused on by the user, tracking the user navigation through an ontology instead of through the structure of a particular site. The content-based recommender module adopts a k nearest neighbours approach and exploits the similarities between the user and document modelling.

Using Information Retrieval to Detect Conflicting Questions

Although e-learning has advanced considerably in the last decade, some of its aspects, such as e-testing, are still in the development phase. Authoring tools and test banks for e-tests are becoming an integral and indispensable part of e-learning platforms and with the implementation of e-learning standards, such as IMS QTI, e-testing material can be easily shared and reused across various platforms. With the knowledge available for reuse and exam automation comes a new challenge: making sure that created exams are free of confl icts. A Confl ict exists in an exam if at least two questions within that exam are redundant in content, and/or if at least one question reveals the answer to another question within the same exam. In this paper we propose using information retrieval techniques to detect confl icts within an exam. Our solution, ICE (Identifi cation of Conflicts in Exams), is based on the vector space model relying on tf-idf weighing and the cosine function to calculate similarity. ICE also combines the hybrid recommendation techniques of the EQRS (Exam Question Recommender System) in order to propose replacements for confl icting questions.

필터링 기법을 이용한 도서 추천 시스템 구축

This study examined several recommendation techniques to construct an effective book recommender system in a library. Experiments revealed that a hybrid recommendation technique is more effective than either collaborative filtering or content-based filtering technique in recommending books to be borrowed in an academic library setting. The recommendation technique based on association rule turned out the lowest in performance.