[INVESTIGATION]: Develop methodology for spam detection

[gtsueng]

Issue Name

Develop methodology for spam detection

Issue Description

Mendeley, Harvard Dataverse, and Zenodo may occasionally get spam submissions. Zenodo has automated spam detection in place which will flag records as spam for removal, though the process can take over a month. It is not clear if Mendeley or Harvard Dataverse are using any sort of automated methods.

Explore the use of LLMs for spam/ad detection

Issue Discussion

This issue as been reported in the Technical reports for July and August 2024

Request Type

Investigation (perform aggregations, analysis, etc.)

Material URL

No response

Related WBS task

https://github.com/NIAID-Data-Ecosystem/nde-roadmap/issues/54

For internal use only. Assignee, please select the status of this issue

• [ ] Not yet started
• [ ] In progress
• [ ] Blocked
• [ ] Will not address

Status Description

No response

Request status check list

• [x] The request has been scoped
• [x] Some immediate discussion or action on the matter was started, but additional investigations are underway
• [ ] The investigation has been conducted
• [ ] The results of the investigation have been made available

[gtsueng]

As mentioned at the meeting dated 2024.09.24, notifying the repositories of spam could be a good opportunity for reaching out to these GREI repositories. We have drafted an email template for such an outreach attempt and a separate issue has been created for it: https://github.com/NIAID-Data-Ecosystem/niaid-feedback/issues/160