cs.CLFeb 24, 2026
SaveEnhancing Hate Speech Detection on Social Media: A Comparative Analysis of Machine Learning Models and Text Transformation Approaches
Organizations: International Institute of Information Technology - Hyderabad Professor CR Rao Rd, Gachibowli Hyderabad 500032, Telangana, India
Abstract
The proliferation of hate speech on social media platforms has necessitated the development of effective detection and moderation tools. This study evaluates the efficacy of various machine learning models in identifying hate speech and offensive language and investigates the potential of text transformation techniques to neutralize such content. We compare traditional models like CNNs and LSTMs with advanced neural network models such as BERT and its derivatives, alongside exploring hybrid models that combine different architectural features. Our results indicate that while advanced models like BERT show superior accuracy due to their deep contextual understanding, hybrid models exhibit improved capabilities in certain scenarios. Furthermore, we introduce innovative text transformation approaches that convert negative expressions into neutral ones, thereby potentially mitigating the impact of harmful content. The implications of these findings are discussed, highlighting the strengths and limitations of current technologies and proposing future directions for more robust hate speech detection systems.
Figures & tables
Figure 1: Percent that agree “People should be able to make statements that are offensive to minority groups publicly” (2015). Source: Pew Research Center.
| Model | Precision (%) | Recall (%) | F1-Score (%) |
|---|---|---|---|
| Lexicon-Based Methods | 62 | 58 | 60 |
| N-Gram Models | 65 | 67 | 66 |
| Support Vector Machines (SVMs) | 70 | 72 | 71 ( Schmidt and Wiegand, 2017b ) |
| Convolutional Neural Networks (CNNs) | 80 | 82 | 81 ( Zhang et al., 2018 ) |
| Recurrent Neural Networks (RNNs) | 78 | 79 | 78.5 |
| Long Short-Term Memory (LSTM) Networks | 82 | 84 | 83 ( Badjatiya et al., 2017 ) |
Table 1: Performance of various models in hate speech detection
Figure 2: Performance of various models in hate speech detection. The graph shows Precision, Recall, and F1-Score for each model.
| # | Column | Non-Null Count | Dtype |
|---|---|---|---|
| 0 | Unnamed: 0 | 24783 | int64 |
| 1 | count | 24783 | int64 |
| 2 | hate_speech | 24783 | int64 |
| 3 | offensive_language | 24783 | int64 |
| 4 | neither | 24783 | int64 |
| 5 | class | 24783 | int64 |
Table 2: Summary of Dataset Attributes
| Attribute | Unique Values |
|---|---|
| Unnamed: 0 | 24783 |
| Count | 5 |
| Hate Speech | 8 |
| Offensive Language | 10 |
| Neither | 10 |
| Class | 3 |
Table 3: Unique Values in Dataset
Figure 3: Distribution of sentiment classes in the dataset.
Figure 4: Distribution of tweet text lengths.
Figure 5: Word cloud of most frequent words in the dataset, highlighting prevalent themes and language.
| Statistic | Unnamed: 0 | Count | Hate Speech | Offensive Language | Neither | Class | Text Length |
|---|---|---|---|---|---|---|---|
| Count | 24783 | 24783 | 24783 | 24783 | 24783 | 24783 | 24783 |
| Mean | 12681.19 | 3.24 | 0.28 | 2.41 | 0.55 | 1.11 | 14.12 |
| Std Dev | 7299.55 | 0.88 | 0.63 | 1.40 | 1.11 | 0.46 | 6.83 |
| Min | 0 | 3 | 0 | 0 | 0 | 0 | 1 |
| 25% | 6372.5 | 3 | 0 | 2 | 0 | 1 | 9 |
| 50% | 12703 | 3 | 0 | 3 | 0 | 1 | 13 |
Table 4: Descriptive Statistics of the Dataset
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.49 | 0.15 | 0.23 |
| Offensive Language | 0.91 | 0.97 | 0.94 |
| Neither | 0.87 | 0.81 | 0.84 |
| Overall Accuracy | 0.897 | ||
Table 5: Classification performance of the CNN model
Figure 6: Model accuracy and learning curves over epochs for the CNN model.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.00 | 0.00 | 0.00 |
| Offensive Language | 0.77 | 1.00 | 0.87 |
| Neither | 0.00 | 0.00 | 0.00 |
| Accuracy (Overall) | 0.774 | ||
Table 6: Classification Performance of the LSTM Model
Figure 7: Accuracy and learning curves over epochs for the LSTM model.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.48 | 0.21 | 0.29 |
| Offensive Language | 0.93 | 0.94 | 0.94 |
| Neither | 0.81 | 0.92 | 0.86 |
| Accuracy (Overall) | 0.899 | ||
Table 7: Classification Performance of the Bi-LSTM Model
Figure 8: Accuracy and learning curves over epochs for the Bi-LSTM model.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.46 | 0.50 | 0.48 |
| Offensive Language | 0.95 | 0.94 | 0.94 |
| Neither | 0.88 | 0.91 | 0.90 |
| Accuracy (Overall) | 0.910 | ||
Table 8: Classification Performance of the BERT Model
Figure 9: Accuracy and learning curves over epochs for the BERT model.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.51 | 0.23 | 0.32 |
| Offensive Language | 0.93 | 0.96 | 0.95 |
| Neither | 0.88 | 0.91 | 0.89 |
| Accuracy (Overall) | 0.913 | ||
Table 9: Classification Performance of the DistilBERT Model
Figure 10: Accuracy and learning curves over epochs for the DistilBERT model.
| Model | Precision (%) | Recall (%) | F1-Score (%) | Loss | Accuracy (%) | Epochs |
|---|---|---|---|---|---|---|
| CNN | 76 | 64 | 67 | 0.286 | 89.7 | 3 |
| LSTM | 26 | 33 | 29 | 0.658 | 77.4 | 3 |
| Bi-LSTM | 74 | 69 | 70 | 0.285 | 90.0 | 3 |
| BERT | 77 | 78 | 78 | 0.245 | 91.0 | 3 |
| DistilBERT | 77 | 70 | 72 | 0.233 | 91.3 | 3 |
Table 10: Comparison of Model Performances
Figure 11: Comparison of Precision, Recall, and F1-Score across models
Figure 12: Overall Performance of Models in terms of Test Accuracy and Loss
Figure 13: Training Accuracy of Models Over Epochs
Figure 14: Evaluation Accuracy of Models Over Epochs
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.54 | 0.33 | 0.41 |
| Offensive Language | 0.93 | 0.95 | 0.94 |
| Neither | 0.82 | 0.86 | 0.84 |
| Accuracy (Overall) | 0.899 | ||
Table 11: Performance metrics of the BERT + CNN model
Figure 15: Model accuracy and learning curves over epochs for the BERT + CNN model integration.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.48 | 0.39 | 0.43 |
| Offensive Language | 0.95 | 0.95 | 0.95 |
| Neither | 0.86 | 0.92 | 0.89 |
| Accuracy (Overall) | 0.911 | ||
Table 12: Performance metrics of the Updated BERT + CNN model
Figure 16: Model accuracy and learning curves over epochs for the Updated BERT + CNN model integration.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.56 | 0.10 | 0.16 |
| Offensive Language | 0.92 | 0.97 | 0.95 |
| Neither | 0.89 | 0.88 | 0.88 |
| Accuracy (Overall) | 0.910 | ||
Table 13: Performance metrics of the DistilBERT + CNN model
Figure 17: Model accuracy and learning curves over epochs for the DistilBERT + CNN model integration.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.52 | 0.20 | 0.29 |
| Offensive Language | 0.93 | 0.96 | 0.95 |
| Neither | 0.87 | 0.92 | 0.90 |
| Accuracy (Overall) | 0.913 | ||
Table 14: Performance Metrics of the BertLSTMForSequenceClassification Model
Figure 18: Model accuracy and learning curves over epochs for the BERT + BI-LSTM model integration.
| Category | Precision | Recall | F1-Score |
|---|---|---|---|
| Hate Speech | 0.51 | 0.36 | 0.42 |
| Offensive Language | 0.94 | 0.96 | 0.95 |
| Neither | 0.89 | 0.89 | 0.89 |
| Accuracy (Overall) | 0.914 | ||
Table 15: Performance metrics of the DistilBert + BI-LSTM model
Figure 19: Model accuracy and learning curves over epochs for the DistilBERT + BI-LSTM model integration.
| Model | Precision (%) | Recall (%) | F1-Score (%) | Loss | Accuracy (%) | Epochs |
|---|---|---|---|---|---|---|
| BERT+CNN | 54.0 | 33.0 | 41.0 | 0.271 | 89.8 | 3 |
| UPDATED BERT + CNN | 48.0 | 39.0 | 43.0 | 0.295 | 91.0 | 3 |
| DISTILBERT+CNN | 56.0 | 10.0 | 16.0 | 0.292 | 91.1 | 3 |
| BERT+BI-LSTM | 52.0 | 20.0 | 29.0 | 0.252 | 91.3 | 3 |
| DISTILBERT+BI-LSTM | 51.0 | 36.0 | 42.0 | 0.246 | 91.5 | 3 |
Table 16: Comparison of Advanced Model Performances
Figure 20: Comparison of Precision, Recall, F1-Score, and Loss across advanced model integrations
Figure 21: Overall Performance of Advanced Model Integrations in terms of Test Accuracy and Loss
Figure 22: Training Accuracy of Advanced Model Integrations Over Epochs
| Model | Precision (%) | Recall (%) | F1-Score (%) | Loss | Accuracy (%) | Epochs |
|---|---|---|---|---|---|---|
| CNN | 76 | 64 | 67 | 0.286 | 89.7 | 3 |
| LSTM | 26 | 33 | 29 | 0.658 | 77.4 | 3 |
| Bi-LSTM | 74 | 69 | 70 | 0.285 | 90.0 | 3 |
| BERT | 77 | 78 | 78 | 0.245 | 91.0 | 3 |
| DistilBERT | 77 | 70 | 72 | 0.233 | 91.3 | 3 |
| BERT+CNN | 76 | 71 | 73 | 0.271 | 89.9 | 3 |
Table 17: Comparative Performance of Basic and Advanced Integrated Models
Figure 23: Overall performance of all models in terms of test accuracy and loss.
Figure 24: Summary of Research Findings