Abstract | ||
---|---|---|
In a world where news is being generated almost continuously by many different news providers on many different platforms, it would be useful in certain industries to be able to determine how much of that news is actually being read, which news items are not interest generating or, indeed, if there are topics being discussed on Twitter that have not even been reported in the news. Twitter generates vast numbers of Tweets daily and has a massive active user base, so it is ideal as a way of gauging what news people are, or are not, interested in. This paper proposes a technique to efficiently relate Tweets to news articles and then to determine which news articles are of interest, which are not, and what is being discussed on Twitter that is not even in the news. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-44748-3_15 | ARTIFICIAL INTELLIGENCE: METHODOLOGY, SYSTEMS, AND APPLICATIONS, AIMSA 2016 |
Keywords | Field | DocType |
Twitter, News articles, Similarity, TF-IDF | World Wide Web,tf–idf,Computer science,News media,Artificial intelligence,Natural language processing | Conference |
Volume | ISSN | Citations |
9883 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tariq Ahmad | 1 | 6 | 1.54 |
Allan Ramsay | 2 | 23 | 8.97 |