Computational Rumor Detection Without Non-Rumor: A One-Class Classification Approach

Amir Ebrahimi Fard, M. Mohammadi, Yang Chen , Bartel van de Walle

Research output: Contribution to journalArticleScientificpeer-review

5 Citations (Scopus)


Rumor spreading in online social networks can inflict serious damages on individual, organizational, and societal levels. This problem has been addressed via computational approach in recent years. The dominant computational technique for the identification of rumors is the binary classification that uses rumor and non-rumor for the training. In this method, the way of annotating training data points determines how each class is defined for the classifier. Unlike rumor samples that often are annotated similarly, non-rumors get their labels arbitrarily based on annotators' volition. Such an approach leads to unreliable classifiers that cannot distinguish rumor from non-rumor consistently. In this paper, we tackle this problem via a novel classification approach called one-class classification (OCC). In this approach, the classifier is trained with only rumors, which means that we do not need the non-rumor data points at all. For this study, we use two primary Twitter data sets in this field and extract 86 features from each tweet. We then apply seven one-class classifiers from three different paradigms and compare their performance. Our results show that this approach can recognize rumors with a high level of F1-score. This approach may influence the predominant mentality of scholars about computational rumor detection and puts forward a new research path toward dealing with this problem.
Original languageEnglish
Article number8804378
Pages (from-to)830-846
Number of pages17
JournalIEEE Transactions on Computational Social Systems
Issue number5
Publication statusPublished - 2019


  • Non-rumor
  • one-class classification (OCC)
  • rumor
  • rumor detection
  • tweet


Dive into the research topics of 'Computational Rumor Detection Without Non-Rumor: A One-Class Classification Approach'. Together they form a unique fingerprint.

Cite this