2022 Fiscal Year Final Research Report
On Trust Representation and Verification Methods for Messages in SNSs
| Project/Area Number |
20K11822
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 60070:Information security-related
|
|---|
| Research Institution | Aichi Institute of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
小田 哲久 愛知工業大学, 経営学部, 非常勤講師 (60131132)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | トラスト / ソーシャルネットワーク / ファジィ論理 / 分散アルゴリズム理論 / 検証 / 災害時分析 |
|---|
| Outline of Final Research Achievements |
This study developed a new trust representation and analysis method by applying a fuzzy logic that allows ambiguous trust evaluations such as "I like it, but I don't like it." We also developed techniques for efficiently analyzing properties related to trust transitions (e.g., the information will become trustworthy someday). We confirmed the applicability of our approach by conducting a case study on analyzing messages on SNS during a disaster. Specifically, we evaluated whether some postings were genuine requests to call a rescue during a flood. In addition, we examined an extension of calculating the integration value in the fuzzy logic (i.e., calculating the net trustworthiness from the trust value, including ambiguity) to handle cases with three or more items, not limited to two (trust and distrust).
|
| Free Research Field |
情報セキュリティ，ファジィ論理
|
| Academic Significance and Societal Importance of the Research Achievements |
ひとたび災害が起こるとＳＮＳには膨大なメッセージが流れるが，救助要請とは無関係なものも多く，要救助者のメッセージは埋もれてしまう．人命に関わるなかで僅かな「本物の救助要請」を選び出す作業は容易ではないが，本研究では，信用度と不信度の組を計算することにより，救助要請としてのトラストを自動的に与えられるようになった．また災害時に限らない一般の場合でも，ネットワーク上のメッセージやユーザの信用度／不信度を，本研究の手法で適切に評価できる．従来手法ではかなわなかった，対象へのこうした柔軟なトラスト評価を，本研究は可能とした．さらに本研究では，トラストの遷移（移り変わり）についての分析も可能となった．
|
