Event Detection Over Twitter Social Media
Twitter is a social networking site that allows a large number of users to communicate with each other. Twitter allows users to share their views on different topics ranging from day to day life to what is going in society. Event detection in twitter is t
- PDF / 309,780 Bytes
- 9 Pages / 439.37 x 666.142 pts Page_size
- 100 Downloads / 271 Views
Abstract Twitter is a social networking site that allows a large number of users to communicate with each other. Twitter allows users to share their views on different topics ranging from day to day life to what is going in society. Event detection in twitter is the process of detecting popular events using messages generated by the users. Event detection is difficult in twitter as compared to other media because the message known as tweets is only allowed to be less than 140 characters. Moreover the tweets are noisy because there may be personal messages by the user also. The focus of this paper is to find top k popular events from tweets using keywords contained in the tweets. This paper also classified the popular events into different categories. Keywords Twitter
⋅
Event detection
⋅
Social media
1 Introduction Twitter is an electronic medium that has gained popularity in recent time. Twitter allows users to post their messages (known as Tweets) on various events. Lengths of tweets are restricted to be less than 140 characters. Twitter gained popularity as it has more than 100 million users in 2012 who has posted 340 million tweets per day. In 2013 Twitter was among the ten top most visited website and given the title of “SMS of the internet”. To post tweets on twitter user has to register himself on the twitter. Users who have not registered themselves on twitter can only read the messages. The relationship between twitter users are of follower and followed type. Sartaj Kanwar (✉) ⋅ Nimita Mangal ⋅ Rajdeep Niyogi Department of Computer Science and Engineering, IIT Roorkee, Roorkee 247667, India e-mail: [email protected] Nimita Mangal e-mail: [email protected] Rajdeep Niyogi e-mail: [email protected] © Springer Science+Business Media Singapore 2017 J.K. Mandal et al. (eds.), Proceedings of the First International Conference on Intelligent Computing and Communication, Advances in Intelligent Systems and Computing 458, DOI 10.1007/978-981-10-2035-3_19
177
178
Sartaj Kanwar et al.
Twitter users have unilateral relationship i.e. when a user A follows user B, it means user A can get all the messages shared by user B but not vice versa. Due to the restriction on length of tweets sometimes it is difficult to put your idea in fixed characters so, users can share link to other objects on internet such as article, blogs, video etc. (termed as artifacts in twitter). As users share what is going around them on twitter and this will be almost instantly. This makes twitter a good source for timely information. Twitter uses the following concept “when you need to know what’s going on-in your town or across the globe-get the best of what’s happening on twitter”. The goal of this paper is to demonstrate how the popular events can be extracted from tweets posted by the twitter users. Events are the incident that is happening at some place at some point of time. As there may be lots of event going on but we are interested in popular event. Popular event is the event which got more attention as compared to other ev
Data Loading...