# Multi-task Pairwise Neural Ranking for Hashtag Segmentation

## TL;DR

This paper introduces a neural pairwise ranking approach for hashtag segmentation, significantly improving accuracy and enhancing downstream sentiment analysis performance.

## Contribution

It presents a novel neural ranking model for hashtag segmentation and demonstrates its effectiveness over existing methods and benefits for sentiment analysis.

## Key findings

- 24.6% error reduction in hashtag segmentation accuracy
- Improved sentiment analysis recall by 2.6%
- New dataset of 12,594 hashtags with segmented annotations

## Abstract

Hashtags are often employed on social media and beyond to add metadata to a textual utterance with the goal of increasing discoverability, aiding search, or providing additional semantics. However, the semantic content of hashtags is not straightforward to infer as these represent ad-hoc conventions which frequently include multiple words joined together and can include abbreviations and unorthodox spellings. We build a dataset of 12,594 hashtags split into individual segments and propose a set of approaches for hashtag segmentation by framing it as a pairwise ranking problem between candidate segmentations. Our novel neural approaches demonstrate 24.6% error reduction in hashtag segmentation accuracy compared to the current state-of-the-art method. Finally, we demonstrate that a deeper understanding of hashtag semantics obtained through segmentation is useful for downstream applications such as sentiment analysis, for which we achieved a 2.6% increase in average recall on the SemEval 2017 sentiment analysis dataset.