# text-along

**Repository Path**: mirrors_ibm/text-along

## Basic Information

- **Project Name**: text-along
- **Description**: Text Along - Subjectivity Analysis Support for Social Impact. Text Along is an interactive editor giving suggestions for replacements to subjective text, to keep the reporting and descriptions factual or neutral, depending on the context.
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-08-04
- **Last Updated**: 2026-07-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# **Introduction** - Welcome to Text-Along

https://github.com/user-attachments/assets/bb28f90b-bb22-46e5-95df-83d4b8a0fae0


# **Project Description**

To date, journalists as well as researchers and practitioners in the social sciences have made extensive manual efforts in addressing the issue of bias in media - screening for subjectivity that could negatively or positively skew or have undue influence on perception of the reader or its subjects. Our team at IBM Research has been working on multiple projects aimed at addressing this issue and making the process of fair report simpler and more convenient. 

Our tool “Text Along - Subjectivity Analysis Support for Social Impact”, can assist users evaluate the likelihood of provided text in negatively or positively skewing their reader’s perceptions.  Text-Along provides suggestions for replacements to subjective text, to help keep the reporting and descriptions factual or neutral, depending on the context. Text Along serves as an interactive editor to writers and journalists by providing feedback and awareness to them of any implicit biases as they formulate their written text - alleviating negative impacts that hurt not only the reader, but the vulnerable communities that are often the subject of these biases.
 
### Publications:
Chiazor, L., de Mel, G., White, G., Newton, G., Pavitt, J., & Tomsett, R. (2021, February). An Automated Framework to Identify and Eliminate Systemic Racial Bias in the Media. In AAAI Conference on Artificial Intelligence. -  https://ceur-ws.org/Vol-2812/RDAI-2021_paper_14.pdf

Andrews, Kenya S., and Lamogha Chiazor. (2024) “Epistemological Bias As a Means for the Automated Detection of Injustices in Text” - https://arxiv.org/abs/2407.06098

## **Where to start** 

[GitHub Pages](https://ibm.github.io/text-along/)

Instructions for running the installation can be found [here](https://github.com/IBM/text-along/blob/main/t4jbias-backend/README.md).

## **To Contibute**
Contributions and improvements are highly welcome.
To contribute to this project, please follow the guidiance as described in our [CONTRIBUTING information](https://github.com/IBM/text-along/blob/main/CONTRIBUTING.md) page. Thanks