A Comparative Study of People-to-People Recommender Algorithms in Hybrid Method
Journal Title: International Journal of the Computer, the Internet and Management - Year 2016, Vol 24, Issue 3
Abstract
Based on Internet Live Stats data, more than 2 billions information has been accessed daily of internet user daily. Amatriain said that trend of searching method has been deprecated. Trend of recommendation method has taken the position nowadays. Information must been processed to be transformed into recommendation and recommendation will reveal hidden information to the right position. One of recommendation method is people-to-people recommendation because one of the most accessed media in internet is social media. This research will discuss about comparison between hybrid algorithm in people-to-people recommendation. There are three algorithms which will be compared: hybrid content-collaborative reciprocal (without using weight) algorithm, hybrid content-collaborative reciprocal (using weight) algorithm, and interactive-based + decision tree algorithm. These algorithm will be implemented in recommending workout partner using “FitParners”, Android-based mobile application and used 200 respondents (active or not active workout). The result will be compared based on execution time in generating the result and accuracy level of recomendation. Interactive-based + decision tree algorithm has best execution time which is 1726 ms. Hybrid content-collaborative reciprocal (using weight) algorithm has best accuracy level which is 76,45%.
Authors and Affiliations
Elizabeth Irenne Yuwono, Nehemia Sugianto
Keywords
Related Articles
- EP ID EP605116
- DOI -
- Views 163
- Downloads 0
E-Learning via Social Media
Social media technology provides educators with an opportunity to engage learners in the online classroom, as well as to support development of learner skills and competencies. Social media is basically a structure that...
A Conceptual Framework of Collaborative-Based Recommender System in Risk Management for Curriculum Management Under the Thai Qualification Framework for Higher Education
The aim of this research is to develop a conceptual framework of collaborative-based recommender system in risk management for curriculum management under the Thai Qualification Framework for Higher Education (TFQ:HEd)....
Internet Usage in Developing an Instrument Evaluation Character Education in the Primary School Based Culture
The aim of this research is to know how far internet usage by teachers in developing an instrument character education evaluation based culture in schools and to develop models instrument evaluation character education....
An Ontological Content-Based Filtering for Book Recommendation
In the past, an automatic book recommendation heavily relies on similarity of content and category as same as other product recommendation. From perspective of readers, contents of books are not the only factor in select...
BKK Management at Vocational School in Semarang
The aim of this research is to know how the implementation of BKK management which includes planning, organizing, implementing, and evaluation as well as the constraints faced by BKK in the placement of graduates. This s...