Spatio - Temporal Storytelling on Twitter
نویسندگان
چکیده
Social media such as Twitter have ushered in alternative modalities to propagate news and developments rapidly. Just as traditional IR and web research matured to modeling storylines from search results and linking documents into stories, we are now at a point to study how stories organize and evolve in mediums such as Twitter. While there has been a plethora of research for mining and connecting entities through text, the task of deriving a story from short, ill-formed text, is a difficult one. Using spatio-temporal analysis on induced concept graphs, we introduce a new set of methods to automatically derive stories over linked entities in tweets. Our approach models a story as a graph of entities propagating through spatial regions in a temporal sequence, and controls search space complexity by suggesting regions of exploration. Experiments on large scale Twitter datasets demonstrate how storylines can be flexibly generated under various syntactic constraints, even without specific endpoints.
منابع مشابه
Visual Storytelling applied to Spatio-temporal and Multi-dimensional Scientific, Business or Statistics Data
This technical paper describes the ancient social ritual: “visual storytelling” – exemplified through telling stories with Statistics eXplorer and related to a domain within statistical data visualization. Stories are made by the analyst that draws us into reflecting on important discoveries and knowledge and is important to the education and dissemination of public statistics. Colleagues of th...
متن کاملA framework for intelligence analysis using spatio-temporal storytelling
Social media have ushered in alternative modalities to propagate news and developments rapidly. Just as traditional IR matured to modeling storylines from search results, we are now at a point to study how stories organize and evolve in additional mediums such as Twitter, a new frontier for intelligence analysis. This study takes as input news articles as well as social media feeds and extracts...
متن کاملMining spatio-temporal information on microblogging streams using a density-based online clustering method
0957-4174/$ see front matter 2012 Elsevier Ltd. A doi:10.1016/j.eswa.2012.02.136 E-mail address: [email protected] Social networks have been regarded as a timely and cost-effective source of spatio-temporal information for many fields of application. However, while some research groups have successfully developed topic detection methods from the text streams for a while, and even som...
متن کاملSTCS-GAF: Spatio-Temporal Compressive Sensing in Wireless Sensor Networks- A GAF-Based Approach
Routing and data aggregation are two important techniques for reducing communication cost of wireless sensor networks (WSNs). To minimize communication cost, routing methods can be merged with data aggregation techniques. Compressive sensing (CS) is one of the effective techniques for aggregating network data, which can reduce the cost of communication by reducing the amount of routed data to t...
متن کامل