Information verification improvement by textual entailment methods

Information verification is significant because the rate of information generation is high and growing every day, generally in social networks. This also causes social networks to be invoked as a news agency for most of the people. Accordingly, information verification in social networks becomes more significant. Therefore, in this paper, a method for information verification on Twitter is proposed. The proposed method employs textual entailment methods for enhancement of verification methods on Twitter. Aggregating the results of entailment methods in addition to the state-of-the-art methods can enhance the outcomes of tweet verification. In addition, as writing style of tweets is not perfect and formal enough for textual entailment, we used the language model to supplement tweets with more formal and proper texts for textual entailment. Although singly utilizing entailment methods for information verification may result in acceptable results, it is not possible to provide relevant and valid sources for all of the tweets, especially in early times by posting tweets. Therefore, we utilized other sources as a user conversational tree (UCT) besides utilizing entailment methods for tweet information verification. The analysis of UCT is based on the pattern extraction from the UCT. Experimental results indicate that using entailment methods enhances tweet verification.