Analysis of the Quality of Academic Papers by the Words in Abstracts Tetsuya Nakatoh 1(B ) , Kenta Nagatani 2 , Toshiro Minami 3 , Sachio Hirokawa 1 , Takeshi Nanri 1 , and Miho Funamori 4 1 Research Institute for Information Technology, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan nakatoh@cc.kyushu-u.ac.jp 2 Graduate School and Faculty of Information Science and Electrical Engineering, Kyushu University, Fukuoka, Japan 3 Kyushu Institute of Information Sciences, Fukuoka, Japan 4 National Institute of Informatics, Tokyo, Japan Abstract. The investigation of related research is very important for research activities. However, it is not easy to choose an appropriate and important academic paper from among the huge number of pos- sible papers. The researcher searches by combining keywords and then selects an paper to be checked because it uses an index that can be eval- uated. The citation count is commonly used as this index, but informa- tion about recently published papers cannot be obtained. This research attempted to identify good papers using only the words included in the abstract. We constructed a classifier by machine learning and evaluated it using cross validation. As a result, it was found that a certain degree of discrimination is possible. Keywords: Bibliometrics · Research investigation · SVM · Citation 1 Introduction The investigation of related research is a very important task for researchers. Therefore, databases of academic papers are now indispensable for researchers. Appropriate keywords generate lists of papers related to keywords from these databases. They may be very long, but in general, several scales are provided. The citation count [1] is the most widely used evaluation scale for an paper. Many databases have a function for sorting the search results of papers by the number of citations. Although the citation count is a useful and objective mea- sure, newly published papers cannot be evaluated. One solution to this problem may be an assessment of the journal in which it was published as a substitute for evaluating the paper directly. The impact factor (IF) is a typical measure used to evaluate academic journals, which reflects the annual average number of citations of papers published in that journal. It is the most frequently used stan- dard. The IF has the ability to imply the relative importance of journals within c  Springer International Publishing AG 2017 S. Yamamoto (Ed.): HIMI 2017, Part II, LNCS 10274, pp. 434–443, 2017. DOI: 10.1007/978-3-319-58524-6 34