Work

NUSS: An R package for mixed N-grams and unigram sequence segmentation

Year: 2025

Type: software-paper

Abstract: NUSS is an R package for segmenting compound text sequences, such as hashtags, using a dual strategy that integrates n-gram segmentation with unigram sequence segmentation. Designed for context-sensitive analysis without training data, it builds custom dictionaries from any corpus and balances segmentation accuracy with computational efficiency. NUSS enhances preprocessing pipelines in text mining, particularly for social media data, and enables robust analysis in sentiment research, topic modeling, and digital discourse studies. It is the first CRAN-published R package dedicated to text segmentation.

Source: SoftwareX

DOI: 10.1016/j.softx.2025.102309

Author: Oskar Kosch

Institution: Krakow University of Economics

Language: English

Topic: Computational and Text Analysis Methods

Subfield: General Social Sciences

Field: Social Sciences

Domain: Social Sciences

Open Access status: gold

Estimated APC paid: $1,200

Funder: Uniwersytet Ekonomiczny w Krakowie