PSSC dataset: Improving spam detection in Persian SMS by providing a comprehensive dataset

Text messaging is widely regarded as one of the most frequently used methods of text communication among mobile phone users. The affordability and widespread use of texting make it an attractive option for advertisers and spammers. Unfortunately, this has resulted in a large volume of spam messages received by users, lowering their overall satisfaction with mobile phone usage. A significant obstacle in the field of Persian SMS spam classification and removal is the lack of a sufficient and diverse database of both legitimate (ham) and spam SMS messages in Persian. To solve the issue of the limited database of ham and spam Persian SMS messages, in this research a comprehensive database was established by gathering 4,389 text messages from various sources and labeling them.سالاری, محمدحسین و شایگان, محمدامین,1402,بهبود تشخیص هرزپیامک در پیامک های فارسی با ارائه یک پایگاه داده جامع,اولین کنفرانس ملی آنالیز داده ها,یاسوج,,,https://civilica.com/doc/1670746