Hate speech detection + Report
Budget: ₹5,000 – ₹5,001 INR
Hate speech detection is critical for applications like controversial event extraction, building AI chatterbots,
content recommendation, and sentiment analysis. We define this task as being able to classify a text comment as racist, sexist, or neither.
The goal of the project is to create models for classifying text contents as offensive (e.g., racist, sexist or other) and to determine the most relevant terminology for each category.
propose a methodology for solving the research question and provide experimental verification of the results obtained according to results evaluation metrics. The emphasis is not on obtaining high performance but rather on the critical reasoning of the results obtained in order to understand the potential effectiveness of the proposed methodology.
Dataset: https://github.com/Vicomtech/hate-speech-dataset
Evaluation strategy
Cross-validation
Structure of the paper
LaTeX report in https://www.overleaf.com/
The results must be documented in a short article of not more than 8 pages
Introduction
Provides an overview of the project and a short discussion on the pertinent literature
Research question and methodology
Provides a clear statement on the goals of the project, an overview of the proposed approach, and a formal definition of the problem
Experimental results
Provides an overview of the dataset used for experiments, the metrics used for evaluating performances, and the experimental methodology. Presents experimental results as plots and/or tables
Concluding remarks
Provides a critical discussion on the experimental results and some ideas for future work
Code in Colab notebook, get data directly from the link
If interested send me a message on what models will you use.
content recommendation, and sentiment analysis. We define this task as being able to classify a text comment as racist, sexist, or neither.
The goal of the project is to create models for classifying text contents as offensive (e.g., racist, sexist or other) and to determine the most relevant terminology for each category.
propose a methodology for solving the research question and provide experimental verification of the results obtained according to results evaluation metrics. The emphasis is not on obtaining high performance but rather on the critical reasoning of the results obtained in order to understand the potential effectiveness of the proposed methodology.
Dataset: https://github.com/Vicomtech/hate-speech-dataset
Evaluation strategy
Cross-validation
Structure of the paper
LaTeX report in https://www.overleaf.com/
The results must be documented in a short article of not more than 8 pages
Introduction
Provides an overview of the project and a short discussion on the pertinent literature
Research question and methodology
Provides a clear statement on the goals of the project, an overview of the proposed approach, and a formal definition of the problem
Experimental results
Provides an overview of the dataset used for experiments, the metrics used for evaluating performances, and the experimental methodology. Presents experimental results as plots and/or tables
Concluding remarks
Provides a critical discussion on the experimental results and some ideas for future work
Code in Colab notebook, get data directly from the link
If interested send me a message on what models will you use.