Reference | Objectives | Lexicon type | Materials | Output |
---|---|---|---|---|
[98] | To introduce SmartSA, a lexicon-based sentiment classification system for social media genres | Hybridise a general-purpose lexicon, SmartSA, SWN | Twitter, Digg, MySpace | Positive and negative |
[99] | To improve the detection of emotional state of patients in Brazilian online cancer communities by using the proposed approach | SentiHealth-Cancer (SHC-pt) | Positive, negative or neutral | |
[100] | To present the results of the systematic analysis of opinion mining (OM) for YouTube comments | Italian sentiment dictionary from the SentiWordNet sentiment lexicons and the MPQA Lexicon | Review from videos of products, English and Italian | Positive, negative or neutral |
[86] | To learn sentiment words based on both content domain and language domain | Corpus-based lexicon generation method | Twitter stock market | Positive and negative |
[101] | To extract aspects, classify aspect-related sentiment and generate an aspect-level summary | Hybrid sentiment classification scheme, lexicon-based (corpus-based approach) SentiWordNet lexicon | Product reviews | Positive and negative |
[102] | To detect sentiment out of textual snippets which express people’s opinions in different languages by proposed methodology | Hybrid approach lexicon Greek Sentiment Lexicon, NRC Word-Emotion Association Lexicon (EmoLex) | Online user reviews in both Greek and English (Greek e-shopping site with various products) | Positive or negative |
[97] | To correlate the distinct twitter comments of statesmen of distinct countries for having concrete knowledge on the application of drugs to patients attacked by COVID-19 | TextBlob lexicon | Positive and negative |