Discovering geographical topics in the twitter stream

Abstract

Micro-blogging services have become indispensable communication tools for online users for disseminating breaking news, eyewitness accounts, individual expression, and protest groups. Recently, Twitter, along with other online social networking services such as Foursquare, Gowalla, Facebook and Yelp, have started supporting location services in their messages, either explicitly, by letting users choose their places, or implicitly, by enabling geo-tagging, which is to associate messages with latitudes and longitudes. This functionality allows researchers to address an exciting set of questions: 1) How is information created and shared across geographical locations, 2) How do spatial and linguistic characteristics of people vary across regions, and 3) How to model human mobility. Although many attempts have been made for tackling these problems, previous methods are either complicated to be implemented or oversimplified that cannot yield reasonable performance. It is a challenge task to discover topics and identify users' interests from these geo-tagged messages due to the sheer amount of data and diversity of language variations used on these location sharing services. In this paper we focus on Twitter and present an algorithm by modeling diversity in tweets based on topical diversity, geographical diversity, and an interest distribution of the user. Furthermore, we take the Markovian nature of a user's location into account. Our model exploits sparse factorial coding of the attributes, thus allowing us to deal with a large and diverse set of covariates efficiently. Our approach is vital for applications such as user profiling, content recommendation and topic tracking. We show high accuracy in location estimation based on our model. Moreover, the algorithm identifies interesting topics based on location and language.

Mercury: A memory-constrained spatio-temporal real-time search on microblogs

“…In addition, several efforts have focused on analyzing microblog data, which include semantic and sentiment analysis [3], [28], [30], decision making [6], news extraction [35], event and trend detection [1], [19], [27], [34], [37], understanding the characteristics of microblog posts and search queries [22], [33], microblogs ranking [11], [39], and recommending users to follow or news to read [14], [32]. Meanwhile, recent work [35], [40] exploited microblogs contents to extract location information that is used to visualize microblog posts on a map [25], [26] and model the relationship between user interests, locations, and topics [15].…”

Geographic Location and Linguistic Diversity: The Use of Intensifiers in Egyptian and Saudi Arabic

“…People come to use language differently when they are geographically separated even with the increasing contact between people due to the unprecedented development in communication channels (Eisenstein, 2014;Hong et al, 2012;Pavalanathan & Eisenstein, 2015). Regional dialects come out of the standard language when speakers of the same language come to live in different geographic locations.…”

“…The case is that in spite of the widespread of social media communication in an unprecedented way, people still use language differently. In their experimental study of geographic location and language modeling, Hong et al (2012) argue that linguistic maps can be identified by means of discovering the geographical spots of Twitter users. Similarly, Eisenstein (2014) stresses that posts on Twitter reflect some well-known regionalisms.…”

Present and Future of Network Big Data

“…On the other hand, the organic integration of different data types poses new challenges to traditional data processing methods. Such as the integration of geographical information and content in the study of social media [6], the combination of space-time information and content information [7] and so on.…”