scholarly journals Comparative Study of Justification Methods in Recommender Systems: Example of Information Access Assistance Service (IAAS)

2021 ◽  
Author(s):  
Kyelem Yacouba ◽  
Kabore Kiswendsida Kisito ◽  
Ouedraogo Tounwendyam Frédéric ◽  
Sèdes Florence
Keyword(s):  
Comparative Study ◽  
Recommender Systems ◽  
Information Access ◽  
Recommendation Systems ◽  
Selection Method ◽  
Item Selection ◽  
User Group ◽  
New Strategy ◽  
Assistance Service

Justification of recommendations increases trust between users and the system but also generates more relevant recommendations than recommendation systems that do not incorporate it. That is why, we conducted a justification study of the recommendation for IAAS. Our comparative study shows that IAAS, which currently does not offer the opportunity to justify recommendations, needs to be improved. From the analysis of justification methods studied in this work, it appears that none of these methods can be used effectively in IAAS. That is why, we proposed a new IAAS architecture that deals separately with item classification and the extraction of the justification has added the item during recommendation generation. The item selection method remains unchanged as we plan to implement a new strategy to filter user’s reviews should now be extended to four elements: the documentary unit, the group of users, the justification and the weight. Opinion A=(UD,G,J,a). Where UD represents the documentary unit, G the user group, J is the justification and a is the weight of the recommendation.

Multi-Criteria Recommender Systems

2017 ◽  
Vol 8 (4) ◽  
pp. 20-48 ◽  
Author(s):  
Ferdaous Hdioud ◽  
Bouchra Frikh ◽  
Brahim Ouhbi ◽  
Ismail Khalil
Keyword(s):  
Decision Making ◽  
Active Learning ◽  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Selection Method ◽  
Item Selection ◽  
Multi Criteria Decision Making ◽  
Selection Approach ◽  
Comprehensive Study

A Recommender System (RS) works much better for users when it has more information. In Collaborative Filtering, where users' preferences are expressed as ratings, the more ratings elicited, the more accurate the recommendations. New users present a big challenge for a RS, which has to providing content fitting their preferences. Generally speaking, such problems are tackled by applying Active Learning (AL) strategies that consist on a brief interview with the new user, during which she is asked to give feedback about a set selected items. This article presents a comprehensive study of the most important techniques used to handle this issue focusing on AL techniques. The authors then propose a novel item selection approach, based on Multi-Criteria ratings and a method of computing weights of criteria inspired by a multi-criteria decision making approach. This selection method is deployed to learn new users' profiles, to identify the reasons behind which items are deemed to be relevant compared to the rest items in the dataset.

Modelling trust networks using resistive circuits for trust-aware recommender systems

2016 ◽  
Vol 43 (1) ◽  
pp. 135-144 ◽  
Author(s):  
Mehdi Hosseinzadeh Aghdam ◽  
Morteza Analoui ◽  
Peyman Kabiri
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Recommender System ◽  
Cold Start ◽  
User Preferences ◽  
Item Selection ◽  
Trust Networks ◽  
Trust Inference ◽  
Trust Information

Recommender systems have been widely used for predicting unknown ratings. Collaborative filtering as a recommendation technique uses known ratings for predicting user preferences in the item selection. However, current collaborative filtering methods cannot distinguish malicious users from unknown users. Also, they have serious drawbacks in generating ratings for cold-start users. Trust networks among recommender systems have been proved beneficial to improve the quality and number of predictions. This paper proposes an improved trust-aware recommender system that uses resistive circuits for trust inference. This method uses trust information to produce personalized recommendations. The result of evaluating the proposed method on Epinions dataset shows that this method can significantly improve the accuracy of recommender systems while not reducing the coverage of recommender systems.

Knowledge-Based Recommendation Systems

2014 ◽  
Vol 10 (2) ◽  
pp. 1-19 ◽  
Author(s):  
Sarah Bouraga ◽  
Ivan Jureta ◽  
Stéphane Faulkner ◽  
Caroline Herssens
Keyword(s):  
Knowledge Base ◽  
Recommender Systems ◽  
Input Data ◽  
Recommendation Systems ◽  
Knowledge Based ◽  
Classification Framework ◽  
Knowledge Content ◽  
Main Ideas

Knowledge-Base Recommendation (or Recommender) Systems (KBRS) provide the user with advice about a decision to make or an action to take. KBRS rely on knowledge provided by human experts, encoded in the system and applied to input data, in order to generate recommendations. This survey overviews the main ideas characterizing a KBRS. Using a classification framework, the survey overviews KBRS components, user problems for which recommendations are given, knowledge content of the system, and the degree of automation in producing recommendations.

The Study of Item Selection Method in CAT

2012 ◽  
pp. 403-415 ◽  
Author(s):  
Peng Lu ◽  
Dongdai Zhou ◽  
Shanshan Qin ◽  
Xiao Cong ◽  
Shaochun Zhong
Keyword(s):  
Selection Method ◽  
Item Selection

Recommender Systems Review of Types, Techniques, and Applications

2015 ◽  
pp. 7260-7270 ◽  
Author(s):  
George A. Sielis ◽  
Aimilia Tzanavari ◽  
George A. Papadopoulos
Keyword(s):  
Recommender Systems ◽  
Recommendation Systems ◽  
Software Tools ◽  
Future Research ◽  
Research Directions ◽  
Different Types ◽  
Future Research Directions

Recommender or recommendation systems are software tools that make useful suggestions to users, by taking into account their profile, preferences and/or actions during interaction with an application or website. They are usually personalized and can refer to items to buy, people to connect to or books/ articles to read. Recommender Systems (RS) aim at helping users with their interaction by bringing to surface the information that is relevant to them, their needs, or their tasks. This article's objective is to present a review of the different types of RS, the techniques and methods used for building such systems, the algorithms used to generate the recommendations and how these systems can be evaluated. Finally, a number of topics are discussed as envisioned future research directions.

Sign in / Sign up

Export Citation Format

Share Document