# Improving Sentiment Analysis with Multi-task Learning of Negation

## TL;DR

This paper introduces a multi-task neural network approach that explicitly models negation to improve sentiment analysis accuracy across multiple datasets.

## Contribution

It presents a novel cascading neural architecture with selective sharing of LSTM layers that explicitly incorporates negation as an auxiliary task, outperforming implicit learning methods.

## Key findings

- Explicit negation modeling improves sentiment classification.
- Multi-task learning with negation enhances performance across datasets.
- The approach is effective with varying data types and amounts.

## Abstract

Sentiment analysis is directly affected by compositional phenomena in language that act on the prior polarity of the words and phrases found in the text. Negation is the most prevalent of these phenomena and in order to correctly predict sentiment, a classifier must be able to identify negation and disentangle the effect that its scope has on the final polarity of a text. This paper proposes a multi-task approach to explicitly incorporate information about negation in sentiment analysis, which we show outperforms learning negation implicitly in a data-driven manner. We describe our approach, a cascading neural architecture with selective sharing of LSTM layers, and show that explicitly training the model with negation as an auxiliary task helps improve the main task of sentiment analysis. The effect is demonstrated across several different standard English-language data sets for both tasks and we analyze several aspects of our system related to its performance, varying types and amounts of input data and different multi-task setups.