Sentilangn: A Language-Neutral Graph-Based Approach For Sentiment Analysis In Microblogging Data

In this paper, we present a language-neutral graph-based sentiment analysis approach, SentiLangN, which uses character n-gram graph for modelling textual data to handle language-neutral unstructured expressions and noisy data. Since ordering and positioning of characters and words in a document plays a vital role in content analysis, the SentiLangN employs the longest common subsequence and degree similarity to capture inherent semantics of the textual data.SentiLangN introduces averaged character n-gram graph model and an application of long-short-term memory (LSTM) approach for sentiment analysis. The performance of SentiLangN is evaluated over real Twitter dataset, and it performs better than the individual n-gram graph models and traditional machine learning algorithms like C4.5. It is also compared with one of the state-of-the-art methods and performs significantly better.