used tweet coordinates to find locations that have been affected by floods.ĭespite the usefulness of historical information extracted from social media, there is not much research addressing the topic of retrospective analysis of this data. used Twitter for real-time earthquake detection, Pak and Paroubek studied Twitter messages as a corpus for sentiment analysis, and Saravanou et al. extracted information to predict the credibility of rumors in social media, Sakaki et al. Just to mention a few examples: Castillo et al. The proof is in the increasing body of scientific work surrounding retrospective microblog data. Nevertheless, it is undeniable that the data poured into social media about world events is of great value to society. So far, historical research had been restricted to traditional archival data and historians’ written account of past events. In particular, the field of comparative historical research examines historical events in comparison to other historical events to gain general knowledge that goes beyond a particular event. Twitter provides excellent conditions for social behavior analysis, as well as comparative historical research, among many other social and scientific disciplines. The particular nature of Twitter messages, as well as the fact that most of its users use the platform from mobile devices, facilitates extremely fast information propagation. When breaking news occurs, Twitter users quickly react by generating content and producing interactions. The messages published in Twitter are called tweets and are constrained to 140-characters. In particular, the social platform Twitter has become a preferred source for users to find up-to-date information. Millions of people from all over the world have assumed the task of reporting and commenting on newsworthy events. Social media users are not only consumers of this information, but also producers and broadcasters. Even traditional mass media organizations such as newspapers and TV news channels now use social media platforms to inform their audience more quickly. Many users exploit social media platforms to obtain information, especially breaking news. We present two case studies of event exploration using Galean and user evaluation of this tool, as well as details of our data mining empirical results.Īs online social networks become massively popular, they are used as reliable and efficient news sources. media, which we explore using data mining techniques on our event representations. The second, a quantitative analysis of a 2-year Twitter dataset of news events reported by U.S. We support our claims by presenting two applications of this idea: the first, a visual tool, named Galean, for retrieval and exploration of historical news events within their geopolitical and temporal context. This facilitates, new information retrieval tasks related to historical event information extraction and international relations analysis. Our hypothesis is that by including social, temporal, and spatial information in the event representation, we are enabling the analysis of historical world news from a social and geopolitical perspective. We call this a spatio-temporal context-aware event representation. This representation explicitly includes temporal information about the event and information about locations, in particular of geopolitical entities. In this work, we target this issue by proposing a compact high-level representation of news events using social media information. As a consequence, tasks related to the analysis of historical news events based on social media data have not been explored, which limits any type of comparative historical research, causality analysis, and discovery of knowledge from patterns extracted from aggregated social media event information. However, as the volume of social media content increases at a very fast rate, it becomes extremely difficult to systematically obtain high-level information from this data. The immense growth of the social Web, which has made a large amount of user data easily and publicly available, has opened a whole new spectrum for research in social behavioral sciences.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |