A Framework for Hoax News Detection and Analyzer used Rule-based Methods

Abstract

Currently, the era where social media can present various facilities can answer the needs of the community for information and utilization for socio-economic interests. But the other impact of the presence of social media opens an ample space for the existence of information or hoax news about an event that is troubling the public. The hoax also provides cynical provocation, which is inciting hatred, anger, incitement to many people, directly influencing behavior so that it responds as desired by the hoax makers. Fake news is playing an increasingly dominant role in spreading Misinformation by influencing people's Perceptions or knowledge to distort their awareness and decision-making. A framework is develope dataset collection of hoax gathered using web crawlers from several websites, using classification techniques. This hoax news will be categorized into several detection parameters including, page URL, title hoax news, publish date, author, and content. Matching each word hoax using the similarity algorithm to produce the accuracy of the hoax news uses the rule-based detection method. Experiments were carried out on eleven thousand-hoax news used as training datasets and testing data sets; this data set for validation using similarity algorithms, to produce the highest accuracy of hoax text similarity. In this study, each hoax news will label into four categories, namely, Fact, Hoax, Information, Unknown. Contributions propose Automatic detection of hoax news, Automatic Multilanguage Detection, and a collection of datasets that we gather ourselves and validation that results in four categories of hoax news that have measured in terms of text similarity using similarity techniques. Further research can be continued by adding objects hate speech, black campaign, blockchain technique to ward off hoaxes, or can produce algorithms that produce better text accuracy.