Portfolio Details

Analyzing Customer Feedback: Sentiment Analysis in Handyman Services Applications

Process

• Data Collection: The data was obtained from Keagel, which reviews the services provided by "Ojol".
• Data Labeling: The data was labeled with the following categories: 1 for "positive" and 0 for "Negative".
• Data Preprocessing: During the preprocessing phase, several steps were taken, including casefolding to convert all text to lowercase, removing numbers, punctuation, and repeated characters, normalizing slang words, and removing common stop words from the text.
• Training Model: The model was trained using the BLSTM (Bidirectional Long Short-Term Memory) algorithm.
• Model Evaluation: The model was evaluated using the Accuracy metric.

Result

The project successfully implemented sentiment analysis on the Kerjamin application, a platform for finding handyman services, using a Bidirectional Long Short-Term Memory (BLSTM) model. The BLSTM model was chosen for its ability to capture contextual information from user reviews and feedback. The sentiment analysis results indicated a high accuracy rate, effectively classifying user sentiments into positive and negative categories. This analysis provided valuable insights into customer satisfaction, highlighting key areas for improvement in the service offerings. The integration of sentiment analysis into Kerjamin enhanced the app's ability to understand user needs and preferences, ultimately contributing to a better user experience and more informed business decisions.