Benchmarking sentiment analysis methods for large-scale texts: A case for using continuum-scored words and word shift graphs
This work addresses the need for benchmarking sentiment analysis methods for large-scale social media texts, but it is incremental as it focuses on improving existing dictionary-based approaches.
The study tested 6 dictionary-based sentiment analysis methods on 4 corpora and found that reliable and meaningful performance requires dictionaries covering a large portion of the lexicon weighted by frequency and using continuous word scores.
The emergence and global adoption of social media has rendered possible the real-time estimation of population-scale sentiment, bearing profound implications for our understanding of human behavior. Given the growing assortment of sentiment measuring instruments, comparisons between them are evidently required. Here, we perform detailed tests of 6 dictionary-based methods applied to 4 different corpora, and briefly examine a further 20 methods. We show that a dictionary-based method will only perform both reliably and meaningfully if (1) the dictionary covers a sufficiently large enough portion of a given text's lexicon when weighted by word usage frequency; and (2) words are scored on a continuous scale.