Design of web application for community answering using Long short-term memory compared over Hybrid Emotion Interface Model with improved accuracy

This study demonstrates a comparison of two different models for a web application for community answering. The first model is a Long Short-Term Memory (LSTM) network and the second is a Hybrid Emotion Interface Model (HEIM). The materials used in the study included a web application for community answering, a large corpus of online community answers, and two machine learning models (LSTM and HEIM). The web application was designed to allow users to ask and answer questions, and also to display the results of the emotion detection algorithms. The LSTM and HEIM models were implemented using the Python programming language and the TensorFlow library. Both models were trained and evaluated on a dataset of community answers collected from a web application. The sample size consisted of 20 participants, divided into two groups of ten each. An investigation was carried out utilizing a G-power of 0.8, with an alpha of 0.05 and p =0.001(p < 0.005), beta of 0.2, and a 95% confidence interval. The results of this study demonstrated that the suggested LSTM model outperformed the traditional HEIM model in terms of accuracy. The LSTM model had an accuracy of 92% while the HEIM model had an accuracy of 87%. Since, there is a significant difference between two algorithms (LSTM and HEIM) hence p =0.001. These findings suggest that the use of the LSTM model may be more effective for evaluating the emotional content of online community answers and helping users to better understand their context.