| Title of Article |
Effect of the inclusion of non-newsworthy messages in credibility assessment
|
| Date of Acceptance |
21 August 2016 |
| Journal |
| Title of Journal |
Advances in Computational Intelligence |
| Standard |
SCOPUS |
| Institute of Journal |
SpringerLink |
| ISBN/ISSN |
978-3-319-62434-1 |
| Volume |
2017 |
| Issue |
|
| Month |
|
| Year of Publication |
2017 |
| Page |
|
| Abstract |
Social media has become influential and a↵ects large public perception. Anyone can post and share messages on social networking sites. However, not all posts are trustworthy. Many online messages con- tain misleading or false information. There has been an extensive research to assess the credibility of social media data. Previous studies evaluate all online messages, which may be inappropriate due to a large amount of such data that can result in ine↵ectiveness of the system. This paper thus studies and presents the e↵ects of the inclusion of such data. Our findings a rm a negative e↵ect of training a model with non-newsworthy data. The degree of performance degradation is also shown to have a strong connection to a degree of non-newsworthiness in training data. |
| Keyword |
Social network analysis, credibility measurement |
| Author |
|
| Reviewing Status |
มีผู้ประเมินอิสระ |
| Status |
ตีพิมพ์แล้ว |
| Level of Publication |
นานาชาติ |
| citation |
true |
| Part of thesis |
true |
| Attach file |
|
| Citation |
0
|
|
|
Publication
Journal Publication
ไทย