Encoder-Decoder Transformers for Textual Summaries on Social Media Content

Abstract

Social media has a leading role to our lives due to radical upgrade of internet and smart technology. It is the primary way of informing, advertising, exchanging opinions and expressing feelings. Posts and comments under each post shape public opinion on different but important issues making social media’s role in public life crucial. It has been observed that people's opinions expressed through social networks are more direct and representative than those expressed in face-to-face communication. Data shared on social media is a cornerstone of research because patterns of social behavior can be extracted that can be used for government, social, and business decisions. When an event breaks out, social networks are flooded with posts and comments, which are almost impossible for someone to read all of them. A system that would generate summarization of social media contents is necessary. Recent years have shown that abstract summarization combined with transfer learning and transformers has achieved excellent results in the field of text summarization, producing more human-like summaries. In this paper, a presentation of text summarization methods is first presented, as well as a review of text summarization systems. Finally, a system based on the pre-trained T5 model is described to generate summaries from user comments on social media.