Recommending Research Articles: A Multi-Level Chronological Learning-Based Approach Using Unsupervised Keyphrase Extraction and Lexical Similarity Calculation

Abstract

A research article recommendation approach aims to recommend appropriate research articles to analogous researchers to help them better grasp a new topic in a particular research area. Due to the accessibility of research articles on the web, it is tedious to recommend a relevant article to a researcher who strives to understand a particular article. Most of the existing approaches for recommending research articles are metadata-based, citation-based, bibliographic coupling-based, content-based, and collaborative filtering-based. They require a large amount of data and do not recommend reference articles to the researcher who wants to understand a particular article going through the reference articles of that particular article. Therefore, an approach that can recommend reference articles for a given article is needed. In this paper, a new multi-level chronological learning-based approach is proposed for recommending research articles to understand the topics/concepts of an article in detail. The proposed method utilizes the TeKET keyphrase extraction technique, among other unsupervised techniques, which performs better in extracting keyphrases from the articles. Cosine and Jaccard similarity measures are employed to calculate the similarity between the parent article and its reference articles using the extracted keyphrases. The cosine similarity measure outperforms the Jaccard similarity measure for finding and recommending relevant articles to understand a particular article. The performance of the recommendation approach seems satisfactory, with an NDCG value of 0.87. The proposed approach can play an essential role alongside other existing approaches to recommend research articles.

Evaluating keyphrase extraction algorithms for finding similar news articles using lexical similarity calculation and semantic relatedness measurement by word embedding

“…3 , we can see that all the keyphrase extraction algorithms except TeKET extract a good number of high-quality keyphrases. However, TeKET performs well on scientific literature in terms of extracting high-quality keyphrases ( Sarwar et al, 2021 ). TeKET computes a cohesive index (CI) between words to extract the final keyphrases.…”

“…TF-IDF is a statistical measure that determines the significance of a keyword by considering its significance in a single document and multiplying it by its significance across all documents in the corpus . However, the previous studies show that the other prominent algorithms such as KEA, KP-Miner, TeKET, and Yake perform better than TF-IDF for scientific literature ( Miah et al, 2021 ; Sarwar & Noor, 2021 ; Sarwar et al, 2021 ). Therefore, due to the different writing styles of news articles, an extensive experiment is needed to compare the known keyphrase extraction algorithms and select an efficient one.…”

“…Based on the computational analysis, these algorithms can be classified into three categories, namely tree-based, graph-based, and statistical-based algorithms ( Rabby et al, 2020 ). TeKET is the only tree-based algorithm that extracts high-quality keyphrases and performs well on research articles ( Rabby et al, 2020 ; Sarwar et al, 2021 ). In addition to tree-based algorithms, several graph-based algorithms have also been proposed.…”