A Hybrid approach for credibility detection in twitter

Download
index.pdf
2014
Gün, Alper
Show full item record
173
views
269
downloads
Nowadays, microblogging services are seen as a source of information. İt brings us a question. Can we trust information in a microblogging service? İn this thesis, we focus on one of the popular microblogging service, Twitter, and try to answer which information in Twitter is credible. Newsworthiness, importance and correctness are the dimensions to be measured in this study. We propose a hybrid credibility analysis which combines feature based and graph based approaches. Our model is based on three types of structures, which are tweet, user and topic. İnitially, we use feature based learning to construct a prediction model. İn the second step, we use the results of this model as input to authority transfer and further refine the credibility scores for each type of node. The same process is used for measuring each of the dimensions of newsworthiness, importance and correctness. Experiment results show that the proposed hybrid method improves the prediction accuracy for each of these credibility dimensions.
Microblogs., Social media., Instant messaging., User-generated content., Online social networks., Blogs.
http://etd.lib.metu.edu.tr/upload/12616868/index.pdf
https://hdl.handle.net/11511/23329
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

A Hybrid Approach for Credibility Detection in Twitter
Gun, Alper; Karagöz, Pınar (2014-06-13)
Nowadays, microblogging services are seen as a source of information. It brings us a question. Can we trust information in a microblogging service? In this paper, we focus on one of the popular microblogging services, Twitter, and try to answer which information in Twitter is credible. Newsworthiness, importance and correctness are the dimensions to be measured in this study. We propose a hybrid credibility analysis which combines feature based and graph based approaches. Our model is based on three types o...
A Hybrid method for toponym recognition on informal Turkish text
Sağcan, Meryem; Karagöz, Pınar; Department of Computer Engineering (2014)
Since accessing the Internet is getting easier and people are more willing to share information on the Internet than the previous generations, the data on such kind of reachable sources are growing very rapidly day by day. Moreover, because of the popularity and widely usage of those sources, the information which researchers and organizations are interested in can be found somewhere in these data collection. The purpose of Information Extraction (IE) is to analyze this information cloud and to extract the ...
A study for the requirements of a quality maturity framework for it facilities in organizations: a case for quality assessment in Turkish institutions
Oray, Emre; Arifoğlu, Ali; Department of Information Systems (2010)
Nowadays, almost all organizations use information technologies (IT) in some extent that they have gained many advantages from it. However, the wrong management of IT processes may cause big problems for organizations. It is first required to reach the quality to successfully govern IT and its processes. At this point, it is essential to have a quality maturity framework that organizations could use to follow a logical path in achieving quality. This thesis represents a study for determining the general qua...
Collective classification of user emotions in twitter
İleri, İbrahim; Karagöz, Pınar; Department of Computer Engineering (2015)
The recent explosion of social networks has generated a big amount of data including user opinions about varied subjects. For classifying the sentiment of user postings, many text-based techniques have been proposed in the literature. As a continuation of sentiment analysis, there are also studies on the emotion analysis. Because of the fact that many different emotions are needed to be dealt with at this point, the problem becomes much more complicated. In this thesis, a different user-centric approach is ...
A Software quality model for android applications
Şimşek, Merve Vildan; Betin Can, Aysu; Department of Information Systems (2016)
Nowadays mobile devices have become increasingly widespread. It causes mobile applications number to grow dramatically. As the popularity of these systems is predicted to continue its increase in the near future, the importance of the quality of mobile applications increases. The aim of this study is to present a quality model for Android applications. We chose applications developed for Android Operating System as our target because of its prevalence in the mobile market. To achieve the aim of the study, w...
Citation Formats
A. Gün, “A Hybrid approach for credibility detection in twitter,” M.S. - Master of Science, Middle East Technical University, 2014.
METU IIS - Integrated Information Service open@metu.edu.tr