Evolutionary symbiotic feature selection for email spam detection
This work presents a symbiotic filtering approach enabling the exchange of relevant word features among different users in order to improve local anti-spam filters. The local spam filtering is based on a Content- Based Filtering strategy, where word frequencies are fed into a Naive Bayes learner. Se...
| Autor principal: | |
|---|---|
| Outros Autores: | , , , |
| Formato: | conferencePaper |
| Idioma: | eng |
| Publicado em: |
2012
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/1822/21405 |
| País: | Portugal |
| Oai: | oai:repositorium.sdum.uminho.pt:1822/21405 |
| Resumo: | This work presents a symbiotic filtering approach enabling the exchange of relevant word features among different users in order to improve local anti-spam filters. The local spam filtering is based on a Content- Based Filtering strategy, where word frequencies are fed into a Naive Bayes learner. Several Evolutionary A l gori thms are expl ored f or f eature sel ecti on, i ncl udi ng the proposed symbi oti c exchange of the most rel evant featuresamong different users. Theexperimentswereconducted using anovel corpusbased on thewell known Enron datasets mixed with recent spam. The obtained results show that the symbiotic approach is competitive. |
|---|