Fake News Detection Through Information Nutrition Extraction.

Status


Abgeschlossene Masterarbeit

Bearbeiter


  • Udaysimha Neralla

Formalia


Zielgruppe
  • AI Master
Voraussetzungen
  • Ability to read and understand papers written in English.
  • Ability to perform academic writing.
  • Strong programming skills (e.g.Java, App programming essential)
  • Lectures Information Retrieval oder Information Mining (essential)

Aufgabenstellung


Detecting fake NEWS is an art of research in the field of Natural Language Processing(NLP). Many researchers have developed different methods to address this issue but the ground truth, claiming an article to be fake or not fake by a reader is his choice. As a food product has Nutrition facts printed on its package, this thesis work tries to provide the possible Nutrition labels for an article based on the work by Fuhr et al. [1]. With these Nutrition facts, the reader/consumer will be provided with the complete statistics (information nutritions) of the article and help his decision making. A mobile application for the topic will be developed to interact with the user.

Fuhr et al. discuss 9 different possible Nutrition facts of any given article: Factuality, Readability, Virality, Emotion/sentiment, Opinion, Controversy, Credibility, Technicality and Topicality. This thesis covers only Readability, Sentiment, opinion, Credibility which also can be named as C.R.O.S of a given article and the rest will be left for future research. The thesis focuses on analyzing NEWS articles in particular. As part of the thesis, an Android mobile application will be developed for the topic and named as Web content Analyzer(WCA).

Tasks:

  • literature scan. This should be done before the actual project starts. Here the student will be given some initial papers. Based on these papers the student should collect more papers, perform a review of all the papers and prepare an oral presentation of 30 mins. providing an intro to the field. This should take 2-3 weeks. Actual work:
  • Preprocessing of data. This can be done automatically using Natural Language Processing techniques.
  • Feature extraction and supervised learning. The student should perform automatic feature extraction and apply machine learning to extract the information nutrition labels. Perfomance of components should be evaluated using standard evaluation metrics.