Academic Text Injection for Recommender Systems (RecSys26)

A dataset related to text injection attacks in recommender systems, likely containing academic or synthetic text data. It originates from a Kaggle user and is associated with the RecSys 2026 conference or a related paper. The dataset's specific content, size, and collection method are not detailed in the provided metadata.

Use Cases

• Benchmarking defense mechanisms against text injection attacks in recommender systems (inferred from domain, verify after download)
• Training or evaluating models for adversarial robustness in NLP-based recommendation (inferred from domain, verify after download)
• Studying the impact of manipulated text inputs on recommendation outputs (inferred from domain, verify after download)

Strengths

• Published on Kaggle, a platform with established data sharing infrastructure.

Limitations

• Metadata is minimal; actual content requires verification after download.
• Row count, file formats, and column definitions are unknown, limiting suitability assessment.
• License and authorship details are absent, which may affect usage rights.

Provenance

Source

Kaggle user 'maximepegane'.

Collection Method

Method of collection or generation is unknown.

Time Range

Temporal coverage is unknown.

Freshness

Last updated date is unknown; freshness unverified.

Geography

Spatial coverage is unknown.