Systems, methods, and devices that classify mobile messages and associated mobile message senders are presented. A communication network can comprise a message abuse detector component (MADC) that evaluates a mobile message, for example, labeled as abusive in an abuse report. The MADC can evaluate information relating to the abuse report, wherein the evaluations can include an abuse-report-hash-ratio, an abuse-report-sender-ratio, correlation of mobile message content to known spam content or non-spam content, and/or evaluation of reputation of the mobile message sender or abuse report sender, etc. Based at least in part on the evaluation, the MADC can classify mobile message as spam, subscription related, or as another type of mobile message, and can identify, select, and execute (e.g., automatically) a desired abuse management action(s) based at least in part on the evaluation and predefined message abuse criteria.