| dc.description.abstract | In today's digital era, where digitization is pervasive, SMS has emerged as a crucial form of
communication. Unlike platforms such as Facebook and WhatsApp, SMS doesn't depend on
an active internet connection. However, the prevalence of spam SMS poses a significant
threat as it can deceive mobile users into divulging confidential information, leading to
severe consequences. Recognizing the gravity of this issue, there is a pressing need to
develop an effective spam filtration solution. The model would be trained to identify spam
messages based on a variety of features, such as the keywords in the messages was sent.
Machine learning algorithms can be used to train a model to identify spam messages, such
as Naive Bayes classifiers serve as straightforward and resilient probabilistic classifiers,
proving especially valuable in tasks related to text classification. The algorithm operates on
the premise of assuming conditional independence among features given a class, providing
a practical initial approximation for real-world scenarios. | en_US |
