Figures index

From

Predicting Stock Investments Based on Sentiment and Historical Price Data

I. O. Olawale, J. Iworiso, I. A. Amaunam

International Journal of Data Envelopment Analysis and *Operations Research*. 2023, 4(1), 1-32
  • Figure 1. Illustration of the SVM principle and of the one-versus-one multiclass classification method (https://www.researchgate.net/figure/Illustration-of-the-SVM-principle-and-of-the-one-versus-one-multiclass-classification_fig2_220098164)
  • Figure 2. Bidirectional lstm model showing the input and output layers (https://www.researchgate.net/figure/Bidirectional-LSTM-model-showing-the-input-and-output-layers-The-red-arrows-represent_fig3_344554659)
  • Figure 3. A transformer model architecture (https://machinelearningmastery.com/the-transformer-model/)
  • Figure 4. The bert model architecture (https://notebook.community/zhreshold/mxnet/contrib/clojure-package/examples/bert/fine-tune-bert)
  • Figure 5. Coca-Cola stock tweet DataFrame.
  • Figure 6. Number of coca-cola tweets over time.
  • Figure 7. Tweet frequency by hour and day of the week
  • Figure 8. Correlation heatmap of numerical columns
  • Figure 9. Top Users by Tweet Count
  • Figure 10. Top words in tweet
  • Figure 11. Scatter plot of retweets and favorites
  • Figure 12. Distribution of token counts within tweets
  • Figure 13. Word cloud plot of coca-cola tweet
  • Figure 14. Distribution of Tweet Lengths
  • Figure 15. Text Preprocessing steps
  • Figure 16. Missing values in data
  • Figure 17. Cleaning of the datetime column
  • Figure 18. Cleaning of the tweet id column
  • Figure 19. Cleaning of the text column
  • Figure 20. Cleaning of the Username column
  • Figure 21. Cleaning of the Ticker column
  • Figure 22. Cleaning of the favourite’s column
  • Figure 23. Cleaning of the retweet’s column.
  • Figure 24. Cleaning of the Followers column
  • Figure 25. Cleaning of the following column
  • Figure 26. Cleaning of the Is_RT column.
  • Figure 27. Sentiment class Distribution of coca-cola stock tweet.
  • Figure 28. Train test validation split
  • Figure 29. Confusion matrix for multi-class classifier (https://geekflare.com/confusion-matrix-in-machine-learning/)
  • Figure 30. A multiclass roc curve (https://www.analyticsvidhya.com/blog/2020/06/auc-roc-curve-machine-learning/)
  • Figure 31. The creation of the tfidfvectorizer for the SVM model
  • Figure 32. Initializing the class weight to handle class imbalance for the Svm model.
  • Figure 33. SVM model showing the predicted sentiment on test set.
  • Figure 34. The PyTorch class defining the RNN model layers.
  • Figure 35. Preparing the necessary data structures to use pre-trained GloVe word embeddings in the rnn model.
  • Figure 36. Initializing the class weights, Loss function and optimizer for the Svm model.
  • Figure 37. RNN model showing the predicted sentiment on test set.
  • Figure 38. The PyTorch class defining the BERT Model classifier.
  • Figure 39. Function to preprocess the BERT classifier.
  • Figure 40. Defining the hyperparameter, optimizer, scheduler, and loss function for the BERT model.
  • Figure 41. BERT model showing the predicted sentiment on test set.
  • Figure 42. SVM Model Result Output.
  • Figure 43. SVM Model Confusion Matrix
  • Figure 44. SVM Model Classification Report
  • Figure 45. SVM Model Multi Class ROC Curve
  • Figure 46. RNN Model Epoch Output
  • Figure 47. Rnn Model Confusion Matrix
  • Figure 48. RNN Model Classification Report
  • Figure 49. RNN Model Loss Plot
  • Figure 50. RNN Model Accuracy Plot
  • Figure 51. RNN Model Multi Class ROC Curve
  • Figure 52. BERT Model Epoch Output
  • Figure 53. BERT Model Confusion Matrix
  • Figure 54. BERT Model Classification Report
  • Figure 55. BERT Model Loss Plot
  • Figure 56. BERT Model Accuracy Plot
  • Figure 57. BERT Model Multi Class ROC Curve
  • Figure 58. Training and Testing Time Comparison Plot
  • Figure 59. Training, Testing and Validation Loss Comparison Plot
  • Figure 60. Precision, Recall and F1 Score Comparison Plot
  • Figure 61. Test and Validation Accuracy Comparison Plot
  • Figure 62. Output of the Sentiment Classified Ten Stocks
  • Figure 63. Determining Follower’s and Retweet’s Mean and Standard Deviation
  • Figure 64. Combined Stock Input
  • Figure 65. DataFrame of the Combined Stock Input
  • Figure 66. showing the dataset, stock sentiment and the combined stock input for all ten stocks.
  • Figure 67. Investment Strategies using Random Forest Classifier
  • Figure 68. Investment Strategies using XGBoost Classifier