DualDet: A Dual-Task Detection Benchmark for Stance and Bot Detection on Social Media

DualDet Dataset Paper DualDet: A Dual-Task Detection Benchmark for Stance and Bot Detection on Social Media. Introduction DualDet integrates inherited bot labels, follower graph context, and new expert annotations for user-level stance. The published dataset covers 124,802 users, with 22,906 users carrying expert stance labels. The benchmark supports the experiments reported in the paper, including stance detection, bot detection, and joint modeling, and highlights measurable stance–bot dependencies. Dataset Format DualDet Location: DualDet.zip/DualDet/unlabeled Contents: each entry corresponds to a single tweet and records author_id, id, and text exactly as extracted from TwiBot-22. Note: the id column here is the tweet id (per-tweet data) and in the workspace version it is hashed, while author_id keeps its original value; the text is stored as a BERT embedding derived from bert-base-uncased. labeled subset Location: DualDet.zip/DualDet/labeled Contents: each record summarizes one user with hashed name, tweets (list of embeddings as generated), stance, follow and id fields that currently remain in their original values in this workspace. Note: id here denotes the user id in its raw form, and follow is the list of follower ids as collected. test Location: DualDet.zip/DualDet/test Contents: rows combine id, name, description, tweets, follow, stance, and account-type. Note: id here denotes the user id in its raw form; in the workspace version, description and tweets store BERT embeddings while name remains hashed and the id/follow fields stay in their original values. How to obtain The processed data above is already available in this workspace. For access to more detailed or raw data releases, please contact the team at [e-mail] using your institutional email. In your request, include your institution, advisor (if any), and intended research use. Ethics & Anonymization DualDet is built from publicly available social media content and licensed under CC BY 4.0 for research use. The corpus may contain sensitive or offensive language, and exposing user-level information increases privacy risks. Please release/use the data in a platform-compliant way, report results at aggregate levels, and audit models for robustness/bias. Misuse risks include political profiling, harassment, or wrongful bot labels—careful handling and ethical review are encouraged before downstream deployment.