A Neural Citation Count Prediction Model based on Peer Review Text

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 4914–4924, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 4914 A Neural Citation Count Prediction Model based on Peer Review Text Siqing Li1,2, Wayne Xin Zhao ∗1,2, Eddy Jing Yin and Ji-Rong Wen1,2 1School of Information, Renmin University of China 2Beijing Key Laboratory of Big Data Management and Analysis Methods {lisiqing,jrwen}@ruc.edu.cn batmanfly@gmail.com eddy_yin@hotmail.com Abstract Citation count prediction (CCP) has been an important research task for automatically esti- mating the future impact of a scholarly paper. Previous studies mainly focus on extracting or mining useful features from the paper itself or the associated authors. An important kind of data signals, i.e., peer review text, has not been utilized for the CCP task. In this paper, we take the initiative to utilize peer review data for the CCP task with a neural prediction model. Our focus is to learn a comprehensive semantic representation for peer review text for improving the prediction performance. To achieve this goal, we incorporate the abstract- review match mechanism and the cross-review match mechanism to learn deep features from peer review text. We also consider integrating hand-crafted features via a wide component. The deep and wide components jointly make the prediction. Extensive experiments have demonstrated the usefulness of the peer review data and the effectiveness of the proposed model. Our dataset has been released online. 1 Introduction In recent years, the number of scientific pub- lications has been growing in a dramatic rate. For example, the numbers of submissions and accepted papers of EMNLP 2019 have increased to 2,877 and 684 respectively1. Given the huge volume of scholarly papers, a long-standing re- search challenge is how to effectively evaluate the impact of scientific literature (Garfield, 1999; Saha et al., 2003; Bornmann, 2013). A typical way to measure the impact of a scholarly paper is through the number of citations received after pub- lication (Garfield, 1979; Aksnes, 2006), reflecting the influence in the research community. ∗Corresponding author 1https://emnlp2019.org Since citation count is an important evaluation measure for scientific impact, many researchers aim to develop automatic ways to predict the future citation of a paper (Castillo et al., 2007; Ibáñez et al., 2009; Davletov et al., 2014; Xiao et al., 2016). A typical approach is to casting the problem into a classification or regression task, focusing on extracting useful feature infor- mation (Yan et al., 2011; Chen and Zhang, 2015; Singh et al., 2015; Park et al., 2017) (e.g., h-index and topic distribution). Although these studies have achieved important progress on this task, they mainly utilize information from the papers themselves or their associated authors. They have neglected an important kind of data signal for the prediction task, i.e., peer review data. Peer review is a widely adopted paper e- valuation mechanism, in which three or more reviewers would be assigned to decide whether to accept or reject a paper. During the review process, …

Content truncated to 500 words