{"title":"多元来源文本生成文献综述","authors":"A. Müngen, Emre Dogan, Mehmet Kaya","doi":"10.1145/3341161.3343510","DOIUrl":null,"url":null,"abstract":"Almost all academic studies include a literature review section. This section is of significance in terms of presenting the value of the suggested method of the researcher and making comparisons. Due to the increasing number of academic papers and the emergence of various directories and indices, the time spent for finding the related previous studies is an important period for the researcher, which consumes a significant amount of time. By means of the suggested method, researchers can access various types of featured publications related to the keyword from different years from a single address. The system also helps to reveal an exemplary and guiding literature review among the found publications by conducting a text generation. The system uses the TF-IDF method for keyword-based publication search and “Template-Based Text Generation” method for the text generation algorithm. In the study, the largest open-access journal platform, TÜBİTAK Dergipark and SOBIAD Citation Index were used as the data set. As a result of the conducted tests, a method that supports the literature review process, even helping to the writing of literature review, was suggested. Along with the fact that there has not been an equivalent of the suggested study, the comparisons for success, “Text Generation” and “Literature Review” were independently calculated and presented.","PeriodicalId":403360,"journal":{"name":"2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Text Generation with Diversified Source Literature Review\",\"authors\":\"A. Müngen, Emre Dogan, Mehmet Kaya\",\"doi\":\"10.1145/3341161.3343510\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Almost all academic studies include a literature review section. This section is of significance in terms of presenting the value of the suggested method of the researcher and making comparisons. Due to the increasing number of academic papers and the emergence of various directories and indices, the time spent for finding the related previous studies is an important period for the researcher, which consumes a significant amount of time. By means of the suggested method, researchers can access various types of featured publications related to the keyword from different years from a single address. The system also helps to reveal an exemplary and guiding literature review among the found publications by conducting a text generation. The system uses the TF-IDF method for keyword-based publication search and “Template-Based Text Generation” method for the text generation algorithm. In the study, the largest open-access journal platform, TÜBİTAK Dergipark and SOBIAD Citation Index were used as the data set. As a result of the conducted tests, a method that supports the literature review process, even helping to the writing of literature review, was suggested. Along with the fact that there has not been an equivalent of the suggested study, the comparisons for success, “Text Generation” and “Literature Review” were independently calculated and presented.\",\"PeriodicalId\":403360,\"journal\":{\"name\":\"2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)\",\"volume\":\"78 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3341161.3343510\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3341161.3343510","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Text Generation with Diversified Source Literature Review
Almost all academic studies include a literature review section. This section is of significance in terms of presenting the value of the suggested method of the researcher and making comparisons. Due to the increasing number of academic papers and the emergence of various directories and indices, the time spent for finding the related previous studies is an important period for the researcher, which consumes a significant amount of time. By means of the suggested method, researchers can access various types of featured publications related to the keyword from different years from a single address. The system also helps to reveal an exemplary and guiding literature review among the found publications by conducting a text generation. The system uses the TF-IDF method for keyword-based publication search and “Template-Based Text Generation” method for the text generation algorithm. In the study, the largest open-access journal platform, TÜBİTAK Dergipark and SOBIAD Citation Index were used as the data set. As a result of the conducted tests, a method that supports the literature review process, even helping to the writing of literature review, was suggested. Along with the fact that there has not been an equivalent of the suggested study, the comparisons for success, “Text Generation” and “Literature Review” were independently calculated and presented.