@techreport{oai:ipsj.ixsq.nii.ac.jp:00224964, author = {甲斐, 尚人 and 義久, 智樹 and 新原, 俊樹 and 矢野, 英人 and 田主, 英之 and Naoto, Kai and Tomoki, Yoshihisa and Toshiki, Shimbaru and Hideto, Yano and Hideyuki, Tanushi}, issue = {24}, month = {Mar}, note = {オープンサイエンス時代の到来により,研究データの公開,利活用に向けた取り組みが盛んに行われている.公開もしくは共有された研究データの分野融合型研究への利活用を考慮した,異分野研究の研究者にも伝わりやすい抄録の記述方法の開発も今後期待される.これまで学術論文の論文誌のように抄録,本文,参照文献という形式をとる,研究データに特化した論文誌が登場してきている.本研究では研究データに特化した論文誌である「Scientific Data」の抄録に着目し,抄録を構成する英文の品詞の出現数,単語数,キーワード数と研究データ論文の被引用数を重回帰分析することで,各品詞等が研究データの利活用に及ぼす影響を考察した.また,それらの結果をもとに,説明変数を名詞,動詞,その他品詞,単語数,キーワード数に設定し,目的変数を被引用数として機械学習を行い,被引用数を予測する分類器を開発した.これにより,今後の研究データ利活用に向けた,研究データ公開の際の抄録記述の留意点についての議論に繋がることを期待する., With the trend of open science, efforts have been made to open and utilize research data. Considering the use of published or shared research data for interdisciplinary research, it is expected to develop a method of writing abstracts that can be easily understood by researchers in different research fields. Journals specializing in research data that have a format of abstract, text, and references like academic journals have emerged. In this study, we focus on the abstract of "Scientific Data", a journal specialized in research data, and examine the influence of each part of speech on the utilization of research data through multiple regression analysis of the number of occurrences of the part of speech, the number of words and the number of keywords in the abstract, and the number of citations to the research data article. Based on these results, we set the explanatory variables as the number of occurrences of nouns, verbs, the other parts of speech, the number of words, and the number of keywords in the abstract, and developed a classifier to estimate the number of citations by machine learning with the number of citations as the objective variable. We hope that this will lead to a discussion of the issues that need to be considered when writing abstracts for publication of research data for future use of research data.}, title = {研究データ論文の抄録を用いた被引用数推定方式:Scientific Data掲載の抄録を例に}, year = {2023} }