Deceptive Online Content Detection Using Only Message Characteristics and a Machine Learning Trained Expert System

Abstract

This paper considers the use of a post metadata-based approach to identifying intentionally deceptive online content. It presents the use of an inherently explainable artificial intelligence technique, which utilizes machine learning to train an expert system, for this purpose. It considers the role of three factors (textual context, speaker background, and emotion) in fake news detection analysis and evaluates the efficacy of using key factors, but not the inherently subjective processing of post text itself, to identify deceptive online content. This paper presents initial work on a potential deceptive content detection tool and also, through the networks that it presents for this purpose, considers the interrelationships of factors that can be used to determine whether a post is deceptive content or not and their comparative importance.

Fake News Detection Model on Social Media by Leveraging Sentiment Analysis of News Content and Emotion Analysis of Users’ Comments

“…Sentiment analysis (SA) is one of the sections that belong to the NLP field [ 11 ] and is responsible for designing and applying models, techniques, and approaches to identify whether a text deals with objective or subjective information [ 55 ] and, in the last case, to identify whether that information was expressed in a negative, neutral, or positive manner [ 56 ] as well as whether it is strong or weak [ 26 ]. The SA method is used in many fields, especially in social media [ 57 ], such as classifying users’ opinions on social media posts [ 58 , 59 ], or knowing the tendencies of the masses in elections and predicting the final results, in addition to controlling public opinion by understanding the public’s attitudes by analyzing users’ opinions about certain situations [ 32 ].…”

“…Another study has indicated that many people have difficulty distinguishing between fake news and real news, irrespective of their gender, age, or educational attainment [ 10 ]. Social media platforms have presented a virtual environment for posting [ 11 ], discussion, exchange of views, and global interaction among users [ 12 ], without restrictions on location, time, or content volume [ 13 ]. A survey conducted in 2017 claimed that 67% of people in the US got their news mainly from social media [ 14 ].…”

Review and assessment of prior work on and future directions for gradient descent-trained expert systems

“…In [51], the system introduced in [20] was evaluated to assess its efficacy for identifying intentionally deceptive online content. Three factors (the textual context, the speaker's background, and emotion) were used to attempt to detect deceptive content.…”

Assessment of the Use of Patient Vital Sign Data for Preventing Misidentification and Medical Errors

“…Several techniques have been proposed to enhance the system, including techniques designed to reduce error [ 41 ], change the way training is performed [ 42 ], and automate network development [ 43 ]. Its use has also been previously demonstrated for a limited number of applications (see, e.g., [ 44 ]).…”