RESUMO
Currently, with the rapid growth of online media, more people are obtaining information from it. However, traditional hotspot mining algorithms cannot achieve precise and fast control of hot topics. Aiming at the problem of poor accuracy and timeliness in current news media hotspot mining methods, this paper proposes a hotspot mining method based on the co-occurrence word model. First, a new co-occurrence word model based on word weight is proposed. Then, for key phrase extraction, a hotspot mining algorithm based on the co-occurrence word model and improved smooth inverse frequency rank (SIFRANK) is designed. Finally, the Spark computing framework is introduced to improve the computing efficiency. The experimental outcomes expresses that the new word discovery algorithm discovered 16871 and 17921 new words in the Weibo Short News and Weibo Short Text datasets respectively. The heat weight values of the keywords obtained by the improved SIFRANK reaches 0.9356, 0.9991, and 0.6117. In the Covid19 Tweets dataset, the accuracy is 0.6223, the recall is 0.7015, and the F1 value is 0.6605. In the President-elects Tweets dataset, the accuracy is 0.6418, the recall is 0.7162, and the F1 value is 0.6767. After applying the Spark computing framework, the running speed has significantly improved. The text mining news media hotspot mining method based on the co-occurrence word model proposed in this study has improved the accuracy and efficiency of mining hot topics, and has great practical significance.
RESUMO
Background Certain metabolites are closely related to the occurrence and development of pulmonary fibrosis, and the related mechanism has not been fully elucidated. It is necessary to explore the trends of various metabolites and causes of pulmonary fibrosis. Objective To discuss the trends of publication and research hotspots of pulmonary fibrosis-related metabolites by bibliometrics. Methods With "pulmonary fibrosis" and "metabolites" in both Chinese and English as primary keywords, literature search was conducted through public online databases: PubMed, Web of Science, SinoMed, and CNKI. NoteExpress 3.0 and Excel 2019 were used to store and organize the collected literature. Analyses included publication year, number of papers, institution, country/region, and journal title. VOSviewer 1.6.10 was used for visual analysis. Keyword co-occurrence was analyzed by setting the minimum threshold for the occurrence of keywords to 5 times. Results The research on pulmonary fibrosis and associated metabolites in foreign language was earlier than that in Chinese language. Since the 1990s, the number of literature showed an increasing trend in both foreign and Chinese language literature. A total of 1 062 articles were published in foreign languages, of which 864 articles contained the authors’ address information. The authors in the United States published 340 articles, followed by China with 196 articles, and then Japan, Germany, and Italy. There were 728 relevant pieces of literature published in Chinese, 709 of which included the authors’ institution information and 350 institutions were involved. North China University of Science and Technology, Shanxi Medical University, Peking University, Zhengzhou University, China Medical University，and Soochow University were the top 6 by number of publication. A total of 255 Chinese journals published 728 Chinese articles, and among them 242 articles (33.24%) were published by 12 journals having published more than ten articles per journal. A total of 1062 articles were published in 609 foreign language journals, and among them 179 articles (16.85%) were published by 8 journals with more than 15 articles published by each journal. The results of keywords co-occurrence analysis suggested that pulmonary fibrosis in association with glucose metabolism, lipid metabolism, amino acid metabolism, nucleotide metabolism, and biological oxidation were the common themes studied at home and abroad. Conclusion The number of publications on pulmonary fibrosis and metabolites has been on the rise in recent years, and the research hotspots include glucose metabolism, lipid metabolism, amino acid metabolism, nucleotide metabolism, and biological oxidation.
