Amazing technological breakthrough possible @S-Logix

Office Address

  • 2nd Floor, #7a, High School Road, Secretariat Colony Ambattur, Chennai-600053 (Landmark: SRM School) Tamil Nadu, India
  • +91- 81240 01111

Social List

Research Proposal in Semi-supervised Misinformation Detection in Social Network

Research Proposal in Semi-supervised Misinformation Detection in Social Network

  Misinformation detection in a social network identifies and verifies all false information. Dissemination of inaccurate information in social media increases due to the easing of accessibility. Detecting the large volume of inaccurate information intentionally or unintentionally propagated is a challenging task. The accuracy of detecting such information is limited while using traditional supervised methods.

  A supervised learning model mainly utilizes a large amount of labeled data that leads to ignorance of the connection between real and fake information. Emerge of a semi-supervised learning model to build misinformation detection possess the ability to tackle such issue. The semi-supervised learning model utilizes unlabeled and labeled data to capture the correlation between real and fake information. Misinformation detection in social media using a semi-supervised method achieves superior accuracy.

  • In the modern social media era, the enormous spread of misinformation has turned into a global risk, inherently affecting public opinion and intimidating social development.

  • Misinformation detection has attained a great deal of attention and thus has become an emerging research topic in recent years.

  • The spread of misinformation in social networks is context-dependent, and topics for chief sources of misinformation have been divulged in research works, including health, politics, finances, and technology trends.

  • Artificial Intelligence (AI) techniques have shown significant promise in diminishing the spread of misinformation.

  • Misinformation detection demands appropriately identifying the misinformation as it is contained in a smaller proportion of all the information on social media and labeling the huge amount of data to train a beneficial classifier.

  • Semi-supervised learning strategy with deep learning models learns from the finite labeled data and the abundance of unlabeled data available.

  • Implementing misinformation detection in social networks using a semi-supervised learning strategy detects misinformation with limited labels and yields high accuracy.