Credibility Analysis for Tweets Written in Turkish by a Hybrid Method
Proceeding: Third International Conference on Data Mining, Internet Computing, and Big Data (BigData2016)Publication Date: 2016-7-21
Authors : Ali Fatih Gündüz Pınar Karagöz;
Page : 55-62
Keywords : Social Media; Information Credibility; Microblogging; Twitter; Data Mining; Machine Learning;
Abstract
In this work, we have studied credibility analysis of microblogging. We collected our data from one of the most important microblogging services, Twitter. Our data set is created from the Turkish tweets written for weekly television programs broadcast in Turkey with political, cultural or financial contents. We adapted a new credibility definition based on three dimensions: being free from offensive words, not being spam and being newsworthy. To analyse credibility of tweets we proposed a method by hybridizing content based techniques with collaborative filtering techniques. The proposed method consists of two phases: supervised learning and graph based improvement. Classification algorithms are applied in the supervised learning phase and results are improved in the graph based phase of the method. We focused on tweet-tweet, tweet-writer and writer-writer relations in the second phase of our study.
Other Latest Articles
- Identification of Musically Induced Emotion: A Machine Learning Based Approach
- Approaches on Personal Data Privacy Preserving in Cloud: A Survey
- Evaluation the Defects of Models Proposed for Social Networks
- Performance Evaluation of Data Placement Structures for Big Data Warehouses
- Feature Engineering in Hybrid Recommender Systems
Last modified: 2016-07-21 23:50:04