Name
Abstract | ||
|---|---|---|
The progress and widespread use of technology, the popularization of social media, and the use of social media as a part of everyday life have made social media a medium of communication. Twitter is one of the most widely used microblog sites today. Millions of tweets shared every day make Twitter a valuable source of data. Timely intervention during natural disasters is very important. In this study, it was aimed to find out and summarize useful information from the tweets taken at the moment of natural disasters and afterwards, and to provide information sources to aid units. Some part of the collected tweet dataset were manually labeled as positive/negative, then classified by machine learning methods. First important tweets selected using classification method then from these important tweets a subset of tweets which summarizes situation selected as summary. For this, a similarity graph was created by looking at the term and semantic similarities between the tweets. Tweets similar to each other on the graph were clustering in the same cluster. Afterward, the most weighted tweet from each cluster was selected and the summary was created. |
Year | Venue | Keywords |
|---|---|---|
2017 | Signal Processing and Communications Applications Conference | tweeter classification,tweeter summarization,graph,clustering |
Field | DocType | ISSN |
Automatic summarization,Graph,World Wide Web,Everyday life,Social media,Information retrieval,Pattern recognition,Computer science,Microblogging,Natural disaster,Artificial intelligence,Cluster analysis | Conference | 2165-0608 |
Citations | PageRank | References |
1 | 0.35 | 3 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ilkin Huseynli | 1 | 1 | 0.35 |
| M. Elif Karsligil | 2 | 73 | 13.69 |