ORIGINAL ARTICLE SHEG: summarization and headline generation of news articles using deep learning Rajeev Kumar Singh 1 • Sonia Khetarpaul 1 • Rohan Gorantla 1 • Sai Giridhar Allada 1 Received: 13 November 2019 / Accepted: 11 July 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020 Abstract The human attention span is continuously decreasing, and the amount of time a person wants to spend on reading is declining at an alarming rate. Therefore, it is imperative to provide a quick glance of important news by generating a concise summary of the prominent news article, along with the most intuitive headline in line with the summary. When humans produce summaries of documents, they not only extract phrases and concatenate them but also produce new grammatical phrases or sentences that coincide with each other and capture the most significant information of the original article. Humans have an incredible ability to create abstractions; however, automatic summarization is a challenging problem. This paper aims to develop an end-to-end methodology that can generate brief summaries and crisp headlines that can capture the attention of readers and convey a significant amount of relevant information. In this paper, we propose a novel methodology known as SHEG, which is designed as a hybrid model. It works by integrating both extractive and abstractive mechanisms using a pipelined approach to produce a concise summary, which is then used for headline generation. Experiments were performed on publicly available datasets, viz. CNN/Daily Mail, Gigaword, and NEWS- ROOM. The results obtained validate our approach and demonstrate that the proposed SHEG model is effectively pro- ducing a concise summary as well as a captivating and fitting headline. Keywords Extractive summarization  Abstractive summarization  Deep learning  Reinforcement learning  NLP  Headline generation 1 Introduction A precis or a summary refers to a shorter version of an article that conveys the most salient information of the entire article. Text summarization could be defined as an act of creating a miniature portrait of an article, i.e., making an article shorter while retaining the most essential parts, thus maintaining the true essence of the document. Creating concise and coherent summaries is one of the critical issues faced by the newspaper industry, as devel- oping a short summary of a huge article is arduous and time-consuming. Summarizing a news article is a necessity for the entire newspaper industry as it is facing stiff chal- lenges due to strong competition from digital media houses. According to a recent study [44], the annual newspaper market in the USA was valued at 27 billion dollars, and it is estimated that this value is going to fall to 17 billion by the year 2025 due to the digital boom. A 2015 report by Microsoft [36] discovered that the average attention span dropped to about 8.5 s from 12 s. We are surrounded by technology everywhere due to the ever- growing use of smartphones, which has led to a paradigm shift in the way we consume news. According to [47], about 80% of the readers never make it past the headline and the traffic of the website can vary as much as 500% depending on the headline. The process of headline gen- eration suddenly seems more important for traditional news houses in order to get people to read their articles. Taking all these factors into account, traditional news houses have all gone online with content that fits on a mobile screen. It is important to have a news summary that is short, crisp, relevant, and unbiased, which can also adapt to the changing landscape of reading habits. & Rajeev Kumar Singh rajeev.kumar@snu.edu.in 1 Shiv Nadar University, Delhi NCR, India 123 Neural Computing and Applications https://doi.org/10.1007/s00521-020-05188-9