A hybrid algorithm to recommend peers on Twitter

Pao Yue-kong Library Electronic Theses Database

A hybrid algorithm to recommend peers on Twitter

 

Author: Meng, Zinong
Title: A hybrid algorithm to recommend peers on Twitter
Degree: M.Sc.
Year: 2013
Subject: Online social networks.
Internet -- Social aspects.
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Computing
Pages: ix, 47 leaves : ill. ; 30 cm.
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2578654
URI: http://theses.lib.polyu.edu.hk/handle/200/6900
Abstract: Nowadays, social media become the main platforms for people to share content, activities and mood, to consolidate connections among them, etc. As to the concept of connections, they refer to the ones which not only are offline-based but online-based. Maintaining connections becomes one of the most important things to the end user. Thus, the way to help end users find tailored peers that are worth to connect with turns out to be the most important thing for an online community to cultivate loyal users. This thesis is talking about a hybrid algorithm in the area of peer recommendation. Due to the big data issue on Twitter, we define a filtering strategy to reduce the number of candidates who might be recommended to the target user. We refine the content-based similarity and graph-based similarity algorithms proposed by other academics. We also define a user model and weighting formula to leverage these two algorithms. According the similarity degree between the candidates and the target user, we recommend top k most similar candidates to the target user as our focused peers. In order to evaluate the effectiveness of our proposed algorithms and other algorithms, we conduct a personalized survey and employ measurements like recall, precision and F1 metric. Based on the evaluation results, we conclude that our hybrid algorithm is better than the pure content-based similarity algorithm and pure graph-based similarity algorithm, which tells a truth that the more information a recommendation generator uses, the more customized and accurate the recommendations will be.

Files in this item

Files Size Format
b25786544.pdf 971.6Kb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information