DEVELOPING AUTOMATED AMHARIC HATE SPEECH POSTS DETECTION MODEL FROM FACEBOOK USING DEEP LEARNING
Domain:
natural language processingRecord type:
paper
Creator:
Sur
Editor:
Kul
Publisher:
Nat
Host:
During the last few years, social activities over the internet especially on social media
platforms increased drastically, but unfortunately, social networks have also become the
place for hate speech proliferation by which most people’s social lives are disturbed
because of hate speech posts and conflicts triggered by those posts. Studies confirm that
online hate speech has different offline consequences. Even though there are a lot of
researches on automated hate speech detection most of them are for other language and
there is a scarcity of labeled data to apply automated analysis and detection methods on
Amharic dataset. Therefore the research on automatic detection of hate speech posts
attracted our attention.
As a solution to those problems, this research aimed to prepare a labeled huge Amharic
dataset by collecting posts and comments from selected Facebook pages of activists that
participated actively. Those Facebook data sets are labeled manually as hate and free based
on the guidelines and pre-processed by applying data cleaning and normalization
techniques. In this research, the recurrent neural network models for automated hate speech
posts detection from Amharic posts on Facebook are developed by using Long Short Term
Memory (LSTM) and Gated Recurrent Unit (GRU) with word uni-grams for feature
extraction and word2vec to represent each unique word by vector representation. The
experiment was conducted on those two models by using 80% of the data set for training
and 10% for validation to train the model and to select the best hyper-parameters
combination for automated hate speech posts detection. The remaining 10% of the dataset
was used for testing the model after training. As a result Parameter combination 12 of LSTM based RNN achieves an accuracy of 97.9% to detect posts as hate speech or free. Which is assured by testing the models using models
performance test and inference on user-generated data.
platforms increased drastically, but unfortunately, social networks have also become the
place for hate speech proliferation by which most people’s social lives are disturbed
because of hate speech posts and conflicts triggered by those posts. Studies confirm that
online hate speech has different offline consequences. Even though there are a lot of
researches on automated hate speech detection most of them are for other language and
there is a scarcity of labeled data to apply automated analysis and detection methods on
Amharic dataset. Therefore the research on automatic detection of hate speech posts
attracted our attention.
As a solution to those problems, this research aimed to prepare a labeled huge Amharic
dataset by collecting posts and comments from selected Facebook pages of activists that
participated actively. Those Facebook data sets are labeled manually as hate and free based
on the guidelines and pre-processed by applying data cleaning and normalization
techniques. In this research, the recurrent neural network models for automated hate speech
posts detection from Amharic posts on Facebook are developed by using Long Short Term
Memory (LSTM) and Gated Recurrent Unit (GRU) with word uni-grams for feature
extraction and word2vec to represent each unique word by vector representation. The
experiment was conducted on those two models by using 80% of the data set for training
and 10% for validation to train the model and to select the best hyper-parameters
combination for automated hate speech posts detection. The remaining 10% of the dataset
was used for testing the model after training. As a result Parameter combination 12 of LSTM based RNN achieves an accuracy of 97.9% to detect posts as hate speech or free. Which is assured by testing the models using models
performance test and inference on user-generated data.