| Project/Area Number |
16K00445
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Library and information science/Humanistic social informatics
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
HAN Dongli 日本大学, 文理学部, 教授 (10365033)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 文献探索 / 機械学習 / クラウドソーシング / 集合知 / 参照理由 / アノテーション / 情報図書館学 |
|---|
| Outline of Final Research Achievements |
Literature survey is the first step of scientific research. However, this process could be quite time-consuming. Previous works aiming to automatically address this issue employ textual similarity or reference-relation between papers, while neither of which is flexible enough for context-specific demands. In this paper, we introduce the idea of using citation-reasons to narrow down the search range for relevant papers. We first propose a method to predict citation-reasons between scientific papers with machine-learning techniques. However, as the machine-learning method seems not accurate enough according to a subject experiment, we then propose another strategy to annotate citation-reasons between papers in a crowdsourcing manner.The experimental results have shown the effectiveness of our proposal.
|
| Academic Significance and Societal Importance of the Research Achievements |
参照ネットワークを辿ることにより関連文献探索を試みる既存研究が複数存在するが、いずれも参照・被参照以外の論文間関係を考慮しておらず、参照ネットワークが広ければ広いほど、文献選定の手間が増えていくため効率的な探索ができない。実験を通して本研究手法の有効性が確認できれば、たとえば「起点論文で用いられている基礎理論がより詳細に紹介されている文献」のようなきめ細かい探索ニーズにも効率的に対応できるようになり、研究者の研究活動に大きな手助けとなることが期待できる。
|
