Named Entity Recognition on E-Mono: An Algorithm Enhancement Applied in Sentiment Analysis

Sentiment analysis plays a crucial role in natural language processing, aiming to categorize emotions expressed in text. One commonly used approach in sentiment analysis is the Extended Max-Occurrence with Normalized Non-Occurrence (EMONO) term weighting scheme. The EMONO scheme extends the Max-Occurrence with Normalized Non-Occurrence (MONO) approach by considering both the occurrence and non-occurrence frequencies of terms in sentiment classes. However, the original E-MONO approach still overlooks the significance of named entities and their associated sentiment. To address this limitation, we propose an enhanced approach that combines the E-MONO term weighting scheme with Named Entity Recognition (NER). By incorporating NER, we aim to improve the accuracy of sentiment analysis by accurately identifying named entities and analyzing sentiment towards specific entities. Additionally, we enhance the EMONO term weighting scheme by introducing extended max-occurrence groups and normalizing non-occurrences, providing a more comprehensive representation of term significance. The combination of NER and the enhanced EMONO term weighting scheme aims to capture the nuanced sentiment expressed towards named entities, leading to improved sentiment analysis results.