Abstract

There is a growing research on sentiment analysis of various languages, which is being supplanted heavily by those same techniques and methods being applied on the mix code or transliterated text for the same purpose. This growing research is a result of necessity created through the advent of social media as well as textual analysis of the data being collected online. This paper, rather than being a pioneer, is about extending that research for further improvement. Herein, we assess the existing status, standards and achievements of the researchers in the given field and supplant it without proposed methodology to increase precision. Although, the current work is a proposal with improvements over established techniques, it is also however going to be quite comparative when it comes to the existing findings. The idea is to not just improve what has already been built or shown to be true, but also check if the simplest approach is still the best way to proceed or not. By this we mean the existing direct supervised learning for sentiment analysis, without much NLP or language specific work. Since we shall be testing our approach against the existing state of the art as well as entering the area previously not under coverage (Marathi transliterated text), this work is bound to make great strides in the field of sentiment analysis.