Sentiment analysis of consultation answers on Alodokter using Support Vector Machine (SVM)

2025-08-03T13:34:05+00:00

In the medical field, fast and accurate access to information is crucial for diagnosis, treatment, and research. Medical information retrieval systems play an essential role in facilitating this access. Despite the abundance of online medical resources, users often face challenges in processing and interpreting information efficiently. Question Answering (QA) systems aim to provide accurate and relevant responses to user queries, making them integral to platforms such as Alodokter, one of the most popular health websites in Indonesia. Alodokter offers vast medical content and allows direct interactions between users and certified medical professionals, making it a rich source of reliable and contextually relevant data. This study explores the implementation of the Support Vector Machine (SVM) method to classify and analyze sentiment in responses found on Alodokter. SVM is a supervised machine learning algorithm known for its high performance in classification tasks, particularly with non-linearly separable data. Its strong generalization capabilities make it well-suited for complex QA data involving diverse linguistic structures and varying medical contexts. Using Alodokter data, this research evaluates SVM performance across different training-testing ratios to identify the most effective configuration. The experimental results demonstrate that the best classification performance was achieved with a 60:40 training-testing ratio, yielding an accuracy of 70%. At this ratio, negative questions achieved 68% precision, 78% recall, and an F1-score of 73%, while positive questions yielded 74% precision, 62% recall, and F1-score of 67%. Conversely, the 50:50 ratio resulted in the lowest accuracy of 59%, with notable imbalances in recall values, particularly for negative questions. In conclusion, SVM proves to be an effective tool for sentiment-based QA analysis on Alodokter, offering valuable insights to improve online health services and enhance user experience in digital healthcare platforms.

Potential of excavation of c sand in Aek Bolon Village as a building material based on the material feasibility requirements test for concrete construction

2025-09-25T14:13:13+00:00

This study analyzed the feasibility of mountain sand in Aek Bolon Village, Balige District, as a fine aggregate in the concrete mixture. The methods used are exploratory and experimental research through laboratory tests at the University of Medan including sludge content, filter analysis, content weight, moisture content, specific gravity, absorption, and compressive strength of concrete aged 28 days. The test results showed a sludge content of 1.25%, Modulus of Fineness (FM) of 2.78 (medium sand), loose content weight of 1.26 gr/cm³ and density of 1.36 gr/cm³, moisture content of 3.63%, specific gravity of 2.40 gr/cm³, absorption of 2.3%, and an average compressive strength of concrete of 25.50 MPa (SNI 7656-2012). All parameters meet the fine aggregate feasibility standard. Thus, the mountain sand of Aek Bolon Village is suitable for use as a concrete mixture for building construction.

Jurnal Teknoreka

Sentiment analysis of consultation answers on Alodokter using Support Vector Machine (SVM)

Potential of excavation of c sand in Aek Bolon Village as a building material based on the material feasibility requirements test for concrete construction