Collecting reference papers from the Internet is one of the most important activities for progressing research and writing papers about their results. Unfortunately, the current process using Google Scholar may not be efficient, since a lot of paper files cannot be accessed directly by the user. Even if they are accessible, their effectiveness needs to be checked manually. In this paper, we propose a reference paper collection system using web scraping to automate paper collections from websites. This system can collect or monitor data from the Internet, which is considered as the environment, using Selenium, a popular web scraping software, as the sensor; this examines the similarity against the search target by comparing the keywords using the Bert model. The Bert model is a deep learning model for natural language processing (NLP) that can understand context by analyzing the relationships between words in a sentence bidirectionally. The Python Flask is adopted at the web application server, where Angular is used for data presentations. For the evaluation, we measured the performance, investigated the accuracy, and asked members of our laboratory to use the proposed method and provide their feedback. Their results confirm the method’s effectiveness.

Nowadays, accessibility to academic papers has been significantly improved with electric publications on the internet, where open access has become common. At the same time, it has increased workloads in literature surveys for researchers who usually manually download PDF files and check their contents. To solve this drawback, we have proposed a reference paper collection system using a web scraping technology and natural language models. However, our previous system often finds a limited number of relevant reference papers after taking long time, since it relies on one paper search website and runs on a single thread at a multi-core CPU. In this paper, we present an improved reference paper collection system with three enhancements to solve them: (1) integrating the APIs from multiple paper search web sites, namely, the bulk search endpoint in the Semantic Scholar API, the article search endpoint in the DOAJ API, and the search and fetch endpoint in the PubMed API to retrieve article metadata, (2) running the program on multiple threads for multi-core CPU, and (3) implementing Dynamic URL Redirection, Regex-based URL Parsing, and HTML Scraping with URL Extraction for fast checking of PDF file accessibility, along with sentence embedding to assess relevance based on semantic similarity. For evaluations, we compare the number of obtained reference papers and the response time between the proposal, our previous work, and common literature search tools in five reference paper queries. The results show that the proposal increases the number of relevant reference papers by 64.38% and reduces the time by 59.78% on average compared to our previous work, while outperforming common literature search tools in reference papers. Thus, the effectiveness of the proposed system has been demonstrated in our experiments.