Problematic English news analysis at different levels: Phrase, sentence, intent, and article

Abstract The rapid spread of disinformation in the news poses a significant risk of negative consequences for society. As a result, detecting misleading news data has become a popular research topic. Correct news sentences often exhibit bias toward individuals, groups, or political parties or undergo alterations to convey specific moods or significance. The definition, annotation, and detection of problematic news sentences are immediate necessities. This research defines SEPSIS properties (SpEculation, oPinion, biaS, and tiwISt) of problematic news sentences. Sentences with any of these properties are referred to as Septic sentences. The current work automatically identifies Septic sentences in English news using deep learning models, namely convolutional neural networks (CNN), long short-term memory (LSTM), bidirectional LSTM (BiLSTM), CNN-BiLSTM, and CNN-BiLSTM with an attention mechanism. Experimental results indicate that CNN-BiLSTM achieves the highest accuracy of 87.75% in identifying Septic sentences. We observe that Septic sentences contain problematic phrases that make them Septic, referred to as Septic phrases. There is an intent behind which the Septic statement is made. We used the conditional random fields (CRF) algorithm to identify Septic phrases and their corresponding intent, achieving 90.20% accuracy in phrase identification and 91.50% accuracy in intent identification. We conducted an ablation study to assess the importance of SEPSIS properties in fake news detection. Machine learning algorithms using Septic sentences as a feature performed about 1% better in fake news identification.