Twitter features distributions across similar labelers
| Autor: | Amal Abdullah AlMansour |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Microblogging
business.industry Arabic Computer science Entertainment industry 02 engineering and technology computer.software_genre 01 natural sciences Class (biology) language.human_language 010305 fluids & plasmas 020204 information systems 0103 physical sciences Similarity (psychology) Credibility 0202 electrical engineering electronic engineering information engineering language Social media Artificial intelligence business computer Natural language processing |
| Zdroj: | 2017 13th International Computer Engineering Conference (ICENCO). |
| DOI: | 10.1109/icenco.2017.8289823 |
| Popis: | This investigation was one part of a study that involved modelling the credibility of Arabic microblogs with disagreed judging credibility labels. We investigated the hypothesis that the most similar and agreed microblogs credibility judges use the same Twitter credibility features to evaluate tweet messages. First, the most similar labelers were identified using different similarity and agreement measures. Then, we used their assigned credibility labels to examine Twitter content and author features distributions. We found that similar and agreed labelers did not continuously correlate with assigning credibility judgments labels harnessing the same Twitter features. Shared similar features between labelers mainly appeared with the most agreed labelers using Krippendorffs alpha coefficient measure resulting in close to 100% features similarity for only the low-credibility class. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|