Experimenting Dynamic Clonal Selection (DCS) for Parallel Multiple Interest Topics of User Profile Adaptation in Content Based Filtering

Due to rapid digital explosion user shows interest towards finding suggestions regarding a particular topic before taking any decision. Nowadays, a movie recommendation system is an upcoming area which suggests movies based on user profile. Many researchers working on supervised or semi-supervised ensemble based machine learning approach for matching more appropriate profiles and suggest related movies. In this paper a hybrid recommendation system is proposed which includes both collaborative and content based filtering to design a profile matching algorithm. A nature inspired Particle Swam Optimization technique is applied to fine tune the profile matching algorithm by assigning to multiple agents or particle with some initial random guess. The accuracy of the model will be judged comparing with Genetic algorithm.

Download Full-text

Using Query Expansion Techniques and Content-Based Filtering for Personalizing Analysis in Big Data

International Journal of Information Technology and Web Engineering ◽

10.4018/ijitwe.2020040104 ◽

2020 ◽

Vol 15 (2) ◽

pp. 77-101

Author(s):

Sadek Menaceur ◽

Makhlouf Derdour ◽

Abdelkrim Bouramoul

Keyword(s):

Big Data ◽

Query Expansion ◽

Information Filtering ◽

User Profile ◽

High Volume ◽

Data Cube ◽

Enrichment Technique ◽

Expansion Technique ◽

Data Context ◽

Content Based Filtering

The recent debates on personalizing analyses in a Big Data context are one of the most solicited challenges for business intelligence (BI) administrators. The high-volume, the high-variety, and the high-velocity of Big Data have produced difficulty in storing, processing, and analyzing data in traditional systems. These 3Vs (volume, velocity, and variety) created many new challenges and make them difficult to extract the specific needs of the users. In addition, the user may be faced with the problem of disorientation; he does not know what information really corresponds to his needs. The information personalization systems aim to overcome these problems of disorientation by using a user profile. The effectiveness of the personalization system in a Big Data context is to demonstrate by the relevance and accuracy of the content of the results obtained, according to the needs of the user and the context of the research. Nevertheless, most of the recent research focused on the relational data warehouse personalizing and ignored the integration of the user context into the analysis of OLAP cubes, which is the first concerned to execute the user's multidimensional queries. To deal with this, the authors propose in this article a dynamic personalizing approach in Big Data context using OLAP cubes, based on the Content-Based Filtering, and the Query Expansion techniques. The first step in the proposal consists of processing the user queries by an enrichment technique in order to integrate the user profile and his searching context to reduce the searching space in the OLAP cube, and use the expansion technique to extend the scope of the analysis in the OLAP cube. The retrieved results are: “as relevant as possible” compared to the user's initial request. Afterward, they use information filtering techniques such as content-based filtering to personalize the analysis in the reduced data cube according to the term frequency and cosine similarity. Finally, they present a case study and experiences results to evaluate and validate their approach.

Download Full-text

Mobile content recommendation system for re-visiting user using content-based filtering and client-side user profile

2013 International Conference on Machine Learning and Cybernetics ◽

10.1109/icmlc.2013.6890864 ◽

2013 ◽

Cited By ~ 4

Author(s):

Worapat Paireekreng

Keyword(s):

Recommendation System ◽

User Profile ◽

Content Recommendation ◽

Client Side ◽

Content Based Filtering

Download Full-text

Tangible Cultural Analytics: The Adoption of Recommender Systems Within Cultural Research

10.32920/ryerson.14644449 ◽

2021 ◽

Author(s):

Ben Ashley

Keyword(s):

Augmented Reality ◽

Collaborative Filtering ◽

Recommender Systems ◽

Recommender System ◽

User Profile ◽

Cultural Research ◽

Augmented Reality Application ◽

Pros And Cons ◽

Object Similarity ◽

Content Based Filtering

The prospect of implementing recommender systems within the context of cultural research has not been explored nearly as much compared to implementation in e-commerce websites and applications. Recommender systems allow for users to be shown new objects either based upon object similarity or based upon what the algorithm thinks the user will like – which can be derived from user feedback and comparing the user to other similar users. This paper discusses how a recommender system could benefit an augmented reality application that enables 3D viewing of artifacts – as part of the Tangible Cultural Analytics (TCA) project at Ryerson University’s Synaesthetic Lab. This paper outlines four recommender systems: 1) content-based filtering, 2) collaborative filtering, 3) cluster models 4) search based models, and 5) hybrid models; discussing the pros and cons to each. Ultimately, a content-based model without the user profile aspect was chosen for this stage in the prototype. This model showed us just how much potential these recommender systems have when helping cultural researchers uncover new relationships and pieces of history through the study and comparison of artifacts.

Download Full-text

On the Smaller Number of Inputs for Determining User Preferences in Recommender Systems

Mathematics ◽

10.3390/math8122138 ◽

2020 ◽

Vol 8 (12) ◽

pp. 2138

Author(s):

Sang-Min Choi ◽

Dongwoo Lee ◽

Chihyun Park

Keyword(s):

Recommender Systems ◽

Recommender System ◽

Recommendation System ◽

Magic Number ◽

User Profile ◽

User Preferences ◽

User Preference ◽

Minimum Number ◽

Movie Recommendation ◽

Content Based Filtering

One of the most popular applications for the recommender systems is a movie recommendation system that suggests a few movies to a user based on the user’s preferences. Although there is a wealth of available data on movies, such as their genres, directors and actors, there is little information on a new user, making it hard for the recommender system to suggest what might interest the user. Accordingly, several recommendation services explicitly ask users to evaluate a certain number of movies, which are then used to create a user profile in the system. In general, one can create a better user profile if the user evaluates many movies at the beginning. However, most users do not want to evaluate many movies when they join the service. This motivates us to examine the minimum number of inputs needed to create a reliable user preference. We call this the magic number for determining user preferences. A recommender system based on this magic number can reduce user inconvenience while also making reliable suggestions. Based on user, item and content-based filtering, we calculate the magic number by comparing the accuracy resulting from the use of different numbers for predicting user preferences.

Download Full-text

SISTEM INFORMASI BURSA KERJA KHUSUS DENGAN REKOMENDASI MENGGUNAKAN METODE CONTENT BASED FILTERING DI STMIK YADIKA BANGIL

JOUTICA ◽

10.30736/jti.v3i1.199 ◽

2018 ◽

Vol 3 (1) ◽

pp. 129

Author(s):

M. Noval Riswandha ◽

Miftakhul Nuryuda

Keyword(s):

Information System ◽

Job Search ◽

Information Search ◽

User Profile ◽

Job Market ◽

Filtering Method ◽

Job Vacancy ◽

The Right ◽

Stock Information ◽

Content Based Filtering

The author makes a special job stock information system (BKK) in STMIK YADIKA Bangil because the job search process for alumni students is currently running less effectively, alumni students should seek information to BKK officers, while BKK officers have to look for alumni data who have not got a job. Therefore, the authors make a special job market information system with recommendations using content based filtering method. Content based filtering method can be used to suggest job vacancy information in accordance with user profile or job seeker so as to facilitate the information search process.System of recommendation in the application of special job market is used to recommend the right job vacancy information for the alumni of the student.In this system expected alumni students Can receive job vacancy information properly and in accordance with the criteria it has

Download Full-text

Tangible Cultural Analytics: The Adoption of Recommender Systems Within Cultural Research

10.32920/ryerson.14644449.v1 ◽

2021 ◽

Author(s):

Ben Ashley

Keyword(s):

Augmented Reality ◽

Collaborative Filtering ◽

Recommender Systems ◽

Recommender System ◽

User Profile ◽

Cultural Research ◽

Augmented Reality Application ◽

Pros And Cons ◽

Object Similarity ◽

Content Based Filtering

The prospect of implementing recommender systems within the context of cultural research has not been explored nearly as much compared to implementation in e-commerce websites and applications. Recommender systems allow for users to be shown new objects either based upon object similarity or based upon what the algorithm thinks the user will like – which can be derived from user feedback and comparing the user to other similar users. This paper discusses how a recommender system could benefit an augmented reality application that enables 3D viewing of artifacts – as part of the Tangible Cultural Analytics (TCA) project at Ryerson University’s Synaesthetic Lab. This paper outlines four recommender systems: 1) content-based filtering, 2) collaborative filtering, 3) cluster models 4) search based models, and 5) hybrid models; discussing the pros and cons to each. Ultimately, a content-based model without the user profile aspect was chosen for this stage in the prototype. This model showed us just how much potential these recommender systems have when helping cultural researchers uncover new relationships and pieces of history through the study and comparison of artifacts.

Download Full-text