Impact of Statistical and Semantic Features Extraction for Emotion Detection on Indonesian Short Text Sentences

2024-09-09T04:20:37+00:00

The ability to detect emotions in short texts is crucial because interpreting emotions on platforms like Twitter can offer insight into social trends and responses to specific events. Additionally, examining emotions in product reviews assists companies in comprehending customer sentiment, allowing them to improve the quality of their products and services. Most research on Indonesian language emotion detection utilizes statistical feature extraction, with limited discussion on the impact of both statistical and semantic feature extraction. Thus, the research aims to detect emotions in short texts equipped with an analysis of the impact of statistical and semantic features. Analysis of the impact of statistical and semantic features on short texts is necessary to identify the most effective approaches, improve detection accuracy, and ensure that the developed systems can better handle the variety and complexity of informal language. The data used are a public dataset originating from Twitter texts and product review texts in e-commerce. The research utilizes statistical features such as Term Frequency Inverse Document Frequency (TF-IDF) and semantic features such as Bidirectional Encoder Representations from Transformers (BERT). The evaluation results show that using semantic features significantly improves the performance of emotion detection in short texts by 13–24%. It is higher than using statistical features. Deep Learning (DL) algorithms based on neural networks have also been proven to outperform Machine Learning (ML) algorithms in detecting emotions in short text. The experimental results and outlines show the potential directions for future development.

Hybrid Stacked Ensemble Regression Model for Predicting Parkinson’s Progression on Protein Data

2024-10-23T07:27:37+00:00

Parkinson’s Disease (PD) is a progressive neurological disorder marked by both motor and nonmotor symptoms. Accurate prediction of disease progression is critical for effective patient management. The research presents a Hybrid Stacked Ensemble Regression (HSER) model for predicting PD progression using protein and peptide data measurements, leveraging the Movement Disorder Society-Sponsored Revision of the Unified Parkinson’s Disease Rating Scale (MDSUPDRS) scores. The researchers integrate three datasets: clinical data, protein data, and peptide data into a comprehensive feature-engineered dataset. The dataset is split into training and testing sets in four configurations for predicting the four UPDRS scores, namely updrs 1, updrs 2, updrs 3, updrs 4. The hybrid approach combines stacking and blending techniques. The researchers select ridge regression, gradient boosting, and extra trees as base models. A meta-model is trained using the algorithms’ out-of-fold estimates (ridge regression). The final predictions are obtained by averaging the predictions of the base models on the test data. The proposed HSER model exhibits enhanced performance compared to baseline models. These results underscore the promise of the hybrid model to enhance the prediction of PD progression, providing valuable insights for personalized treatment strategies. Future research can focus on refining model weights and exploring additional biomarkers to improve predictive accuracy.

CommIT (Communication and Information Technology) Journal

Impact of Statistical and Semantic Features Extraction for Emotion Detection on Indonesian Short Text Sentences

Hybrid Stacked Ensemble Regression Model for Predicting Parkinson’s Progression on Protein Data