| Project/Area Number |
18K18604
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 8:Sociology and related fields
|
|---|
| Research Institution | Kagawa University |
|---|
Principal Investigator |
Takaaki Aoki 香川大学, 教育学部, 准教授 (30553284)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
時岡 晴美 香川大学, 教育学部, 教授 (10155509)
川本 達郎 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 研究員 (10791444)
|
|---|
| Project Period (FY) |
2018-06-29 – 2022-03-31
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
Fiscal Year 2020: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2019: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
Fiscal Year 2018: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
|---|
| Keywords | アンケート分析 / コミュニティ分解 / ネットワーク科学 / 自由記述式アンケート / 機械学習 |
|---|
| Outline of Final Research Achievements |
Why did you become a scientist? You may have your own story, and such individual answer can be stimulating and informative. But, how do we summarise the answers from many people? This is a major scientific issue in open-ended surveys called coding. To perform statistical analysis, individual responses must be classified into several groups, capturing the underlying semantics that respondents expressed. This manual task can be difficult, subjective, and time-consuming, and this bottleneck has limited the utility of large-scale surveys.
We proposed a network-based survey method in which responses are automatically classified in a statistically principled manner, and demonstrated it using a survey taken by graduates of a university. The method allows us to ask open-ended questions to large populations, such as ``What is the strongest point of our service?'' or ``Why did you buy this product?''. This would bring substantial benefits for society and industry.
|
| Academic Significance and Societal Importance of the Research Achievements |
近年、インターネットを介したオンライン調査によって，１万人以上の人々から多様な意見を収集することが可能になった．この手法を活用することで、「どうして研究者を目指したのですか？」「大学で学んで良かったことはなんですか？」といった「なぜ？」「どうして？」を問いかける大規模な自由記述式アンケートを実施し，その大量の回答から意見グループを自動抽出し，統計分析することが可能となる．世論調査・顧客調査などに活用し，より良い製品開発や社会実現のために役立てることが出来る．
|
