Detected Source-based fake news via Word2vec algorithm

journal of Artificial Intelligence in Electrical Engineering

دوره 10، شماره 37، شهریور 2021، صفحه 44-52   

نوع مقاله: Original Article

نویسندگان

Hamid Sharifi Heris^* ؛ Jafar Sheykhzadeh

Computer science department, Azad University, Ahar, Iran

چکیده

today and regarding the increase of social media platforms and the people welcoming these networks has led to share different data throughout the world without the confirmation by the platforms. This has increased the incorrect data frequency and has had great effects on political, economic, and social fields. such incorrect data are called fake news. This has changed into one of the topical issues in today’s society. Through the proposal of an appropriate solution and first through analyzing the news resources in the dataset called BuzzfeedNews, we have concluded that websites with better fames propagate less fake news. We changed the data into vector using Word2vec and investigated the similarity of the taught data and the tagged data in the dataset and got the least precision amounting to 0.60 and the highest precision amounting to 0.94 out of 1 and the results showed that our algorithm has been very helpful in discovering the qualified news.

کلیدواژه‌ها

fake news detection؛ machine learning؛ word2vec؛ data mining