System and method for slang sentiment classification for opinion mining

A data processing computing device comprising:

• at least one processor;
• a memory coupled to the processor and configured to be capable of executing programmed instructions comprising and stored in the memory to:
• mine at least one database to obtain at least one electronic document comprising textual data about a product;
• transform the textual data in the at least one electronic document to a common electronic format, wherein the transform further comprises normalization of the textual data;
• classify the transformed textual data into subjective context or objective context, wherein the classifying further comprises inserting a tag in the textual data based on the classification;
• identify at least one of a plurality of sentiment oriented slang terms in the transformed textual data with the inserted subjective context tag;
• determine a polarity score for each of the identified at least one of the plurality of sentiment oriented slang terms based on a calculated value for each of the identified at least one of the plurality of sentiment oriented slang terms;
• transform the determined polarity of score for each of the identified at least one of the plurality of sentiment oriented slang terms based on a weighting factor applied to at least one of the determined polarity of scores for each of the identified at least one of the plurality of sentiment oriented slang terms to determine a sentiment score;
• and
• output a sentiment classification of the product based on the determined sentiment score.

A non-transitory computer readable medium having stored thereon instructions for sentiment mining comprising machine executable code which when executed by at least one processor, causes the processor to perform steps comprising:

• mining at least one database to obtain at least one electronic document comprising textual data about a product;
• transforming the textual data in the at least one electronic document to a common electronic format, wherein the transforming further comprises normalization of the textual data;
• classifying the transformed textual data into subjective context and objective context;
• identifying at least one of a plurality of sentiment oriented slang terms in the transformed textual data that is classified as subjective context;
• determining a polarity score for each of the identified at least one of the plurality of sentiment oriented slang terms based on a calculated value for each of the identified at least one of the plurality of sentiment oriented slang terms;
• transforming the determined polarity of score for each of the identified at least one of the plurality of sentiment oriented slang terms based on a weighting factor applied to at least one of the determined polarity of scores for each of the identified at least one of the plurality of sentiment oriented slang terms to determine a sentiment score;
• and
• outputting a sentiment classification of the product based on the determined sentiment score.