Exploring Significant Characteristics and Models for Classification of Structure Function of Academic Documents

Abstract

With the increasing abundance of literature resources, how to acquire knowledge elements efficiently and accurately is the key to achieving accurate literature retrieval and utilization of available literature resources. The identification of the structure function of academic documents is a fundamental work to meet the above requirements. In this study, the proceedings of the Association for Computational Linguistics (ACL) conferences are used as the primitive corpus, and the training corpus of chapter category is obtained by manual annotation. Based on the chapter titles and the in-chapter texts, traditional machine learning and deep learning models are both used for classifier training. Our results show that the title of a chapter is more beneficial to the identification of the structure function of academic documents than the in-chapter texts. The highest F1 value in our experiments is 0.9249, which is obtained on the traditional logistic regression (LR) and support vector machine (SVM) models (slightly higher than on the convolutional neural network [CNN]). And through the experiment of adding other chapter characteristics based on the traditional model, we find that combining the relative position of chapters can effectively improve the classification performance. Finally, this study compares the results of experimental groups with different methods, analyzes the misclassification of the structure function of academic documents, and points out the main direction to improve the classification performance in the future.

Which structure of academic articles do referees pay more attention to?: perspective of peer review and full-text of academic articles

“…The F 1 value is 97.50% which is higher than several traditional methods. Ma et al. (2020) hold a similar view and thought that identifying the structure of academic papers was the basis for achieving accurate retrieval of academic papers.…”

“…The F1 value is 97.50% which is higher than several traditional methods. Ma et al (2020) hold a similar view and thought that identifying the structure of academic papers was the basis for achieving accurate retrieval of academic papers. They found that the section title was more beneficial than the in-section text while identifying the article structure based on 3,992 articles from ACL.…”

Research on the structure function recognition of PLOS

“…Lu et al ( 2014 ) used vocabulary and sequence annotation methods to identify the structural functions of chapters, but however process for identifying titles containing unknown words still needs to be improved. Bowen Ma shows that the title of a chapter is more beneficial to the identification of the structure-function of academic documents than the in-chapter texts (Ma et al, 2021 ). Bowen Ma finds that compared with the chapter content; the chapter title is more conducive to identifying the structure of academic articles (Ma et al, 2022 ).…”

“…words still needs to be improved. Bowen Ma shows that the title of a chapter is more beneficial to the identification of the structurefunction of academic documents than the in-chapter texts (Ma et al, 2021). Bowen Ma finds that compared with the chapter content; the chapter title is more conducive to identifying the structure of academic articles (Ma et al, 2022).…”