Polarity Determination using Opinion Mining in Stocks and Shares-advertising Unsolicited Bulk e-mails

Abstract—e-mail has become an important means of electronic communication but the viability of its usage is marred by Un-solicited Bulk e-mail (UBE) messages. UBE consists of many types like pornographic, virus infected messages, ‘cry-for-help’ messages as well as fake and fraudulent offers/advertisements/promotions of stocks and shares, jobs, winnings, and medicines. UBE poses technical and socio-economic challenges to usage of e-mails. To meet this challenge and combat this menace, we need to understand UBE. Towards this end, a content-based textual analysis of more than 3100 stocks and shares-advertising unstructured UBE documents is presented. The paper is aimed at polarity determination of such UBE through its sentiment analysis. Technically, this is an application of Opinion Mining approached with help of Text Parsing, Tokenization, BOW and VSDM techniques. Sentiment Analysis is used to determine the polarity of the document because such UBE contain opinion of the spammer about specific stock symbol of share market. The Sentiment-depicting words are analyzed in the UBE corpus, scaled and extremes of positive and negative opinions are identified. An attempt has been made for polarity-based distribution of such UBE. It has been found that for almost 50% of cases, the opinions expressed through such UBE have positive polarity, almost 30% cases are negatively opined whereas almost 20% cases contain neutral opinion. To the best knowledge and based on review of related literature, determination of UBE polarity using Opinion Mining for understanding spammer behaviour is a new concept.