A Link Prediction Strategy for Personalized Tweet Recommendation through Doc2Vec Approach

Mojtaba Zahedi Amiri, Abdullah Shobi


Nowadays with growth of using Internet as a principle way of communication, likes different social medias channels (Twitter, Facebook, etc.) and also access to huge amount of information like News, there appear a main research subject to help users to find his/her interests among vast amount of relevant and irrelevant information. Recommender systems are helped to handle information overload problem and in this paper we introduce our Tweet Recommendation System that implement users Twitter information (Tweets, Retweet, Like,...) as a source of user’s information. In this work the semantic of tweets that regard as a User’s Explicit Interests (e.g., person, events, product mentioned in user’s tweets) are identified with the Doc2vec approach and recommend similar tweets through link-prediction strategy. The experiment results show that Doc2Vec approach is a better approach than the other previous approaches.

Full Text:


DOI: https://doi.org/10.22158/rem.v2n4p63


  • There are currently no refbacks.

Copyright (c) 2017 Mojtaba Zahedi Amiri, Abdullah Shobi

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © SCHOLINK INC.  ISSN 2470-4407 (Print)  ISSN 2470-4393 (Online)