This paper proposes the approach based on machine learning for detection of Thai clickbait. The clickbait messages often adopt eye-catching on wording, lagging of information on a content to attract visitors. We contribute the clickbait corpus by crowdsourcing, 30,000 of headlines are selected to draw up the dataset. In this work attempt to develop clickbait detection model using two type of features in the embedding layer and three different of networks in the hidden layer. BiLSTM with word level embedding performs very well achieving accuracy rate of 0.98, fl-score of 0.98.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL