2026-10-12T14:32:02Z https://data.mendeley.com/oai

oai:data.mendeley.com/zk3kn68xz2.1 2026-09-14T09:46:22Z

miao, zhiqin Linguistic Features and Framing Construction in Identity - Impersonation Frauds: A Natural Language Processing - Based Study on Telecommunication Network Fraud Mendeley Data This dataset contains 100 identity-impersonation telecommunication fraud messages targeting university students, collected from the National Anti-Fraud Center App and victim interviews. The research assumes that fraudulent messages exhibit distinct linguistic style and content-based cues that enable detection. Using TextMind and machine learning (TF-IDF, LDA) combined with grounded theory coding, we identified 10 high-frequency linguistic categories (e.g., function words, pronouns, cognitive mechanisms) and 7 content themes (e.g., authority impersonation, time pressure, benefit inducement). The dual-dimensional framework achieved 82.1% detection accuracy (AUC = 0.86), outperforming single-dimension models. Each message includes linguistic frequency scores, topic ratings, and victim outcome (compliance vs. non-compliance). Researchers can use the data for predictive modeling, cross-method validation, or replication of fraud detection analyses. All personal identifiers have been removed. Linguistics Telecommunication Cognitive Psychology Criminology Dataset doi:10.17632/zk3kn68xz2.1 oai:data.mendeley.com/zk3kn68xz2.1 Creative Commons Attribution 4.0 International http://creativecommons.org/licenses/by/4.0 https://data.mendeley.com/datasets/zk3kn68xz2 2026-09-14T09:46:22Z