Abstract: SMS spam, also referred to as mobile spam, has become a prevalent and an ever growing issue thanks to the supply of bulk SMS services at nominal costs. These spam messages might not only be commercial but also pose an excellent deal of monetary threats to the users. To fight against SMS spam, a spread of solutions are proposed including content-based filtering, semantic indexing, machine learning classifiers, etc. However, during this regard evolutionary algorithms haven't been utilized. Since the character of SMS is contemporary, the representation of text messages keep evolving with the assistance of slangs, symbols, misspelled words, abbreviations and acronyms. Hence, such an answer is required which may accommodate these changes, also keeping the length of SMS in consideration. The model proposed during this paper generates regular expressions as individuals of population, using Genetic Programming Approach. These regular expressions so generated are used for the classification purpose. The application of Genetic Programming in the domain of SMS spam filtering has not been explored widely. It is able to eliminate False Positive errors, thus saving legitimate messages from being misclassified. The performance tends to enhance with higher number of generations.
Keywords: Short Message Service, Spam, Genetic algorithm.
| DOI: 10.17148/IJARCCE.2021.10217