Evaluating the learning process requires a platform for students to express feedback and suggestions openly through online reviews. Sentiment analysis is often used to analyze review texts but typically captures only overall sentiment without identifying specific aspects. This study develops an aspect-based sentiment analysis (ABSA) model using IndoBERT, a pre-trained model tailored for the Indonesian language. The research uses 10,000 student reviews from Indonesian universities, processed through data labeling, text preprocessing, and splitting, followed by model training and performance evaluation. The model demonstrated superior performance with an aspect extraction accuracy of 0.973, an F1-score of 0.952, a sentiment classification accuracy of 0.979, and an F1-score of 0.974. Experimental results indicate that the proposed ABSA model surpasses previous state-of-the-art models in analyzing sentiment related to specific aspects of educational evaluation. By leveraging IndoBERT, the model effectively handles linguistic complexities and provides detailed insights into student experiences. These findings highlight the potential of the ABSA model in enhancing learning evaluations by offering precise, aspect-focused feedback, contributing to strategies for improving the quality of higher education.

Sentiment analysis is a field of study that analyzes sentiment. One method for doing sentiment analysis is Latent Dirichlet Allocation (LDA) that extracts the topic of documents where the topic is represented as the appearance of the words with different topic probability. Therefore, we need data representation in visual form that is easier to understand than text and tables. One form of data visualization is wordcloud that provides a visual representation of words frequency. This research will perform sentiment analysis from the students' comments toward a university, in this case the Universitas Diponegoro, using LDA and topic polarity wordcloud visualization. The purpose of this study is to generate the topic polarity wordcloud of the students' comments by using the best combination of parameters. The best combination is the parameter with the value of alpha 0.1, value of beta 0.1, number of topics 9, threshold 10 ^-7 , and perplexity values 8.07. Such parameter combination produces 3 topics as positive sentiment and 6 topics as negative sentiment. In addition, we also compare the proposed method to several algorithms such as Naïve Bayes and Logistic Regression. The final result shows that the proposed method outperforms the Naïve Bayes and Logistic Regression in terms of F-Measure by 61%, 54%, and 56%, respectively.

Scene classification based on latent Dirichlet allocation (LDA) is a more general modeling method known as a bag of visual words, in which the construction of a visual vocabulary is a crucial quantization process to ensure success of the classification. A framework is developed using the following new aspects: Gaussian mixture clustering for the quantization process, the use of an integrated visual vocabulary (IVV), which is built as the union of all centroids obtained from the separate quantization process of each class, and the usage of some features, including edge orientation histogram, CIELab color moments, and gray-level co-occurrence matrix (GLCM). The experiments are conducted on IKONOS images with six semantic classes (tree, grassland, residential, commercial/industrial, road, and water). The results show that the use of an IVV increases the overall accuracy (OA) by 11 to 12% and 6% when it is implemented on the selected and all features, respectively. The selected features of CIELab color moments and GLCM provide a better OA than the implementation over CIELab color moment or GLCM as individuals. The latter increases the OA by only $∼2$ to 3%. Moreover, the results show that the OA of LDA outperforms the OA of C4.5 and naive Bayes tree by $∼20%$.

In this study, we present a web-based application that retrieves hotel review documents in Indonesian languages from an online travel agent (OTA) and analyses their sentiments from the coarse-grained document to the fine-grained aspect level. /Methodology/Approach: There are four main stages in this study: development of sentiment analysis model at the document level based on a convolutional neural network (CNN), development of sentiment analysis model at the aspect level based on an improved long short-term memory (LSTM), model deployment for multilevel sentiment analysis in a web-based application, and its performance evaluation. The developed application uses several sentiment visualizations types at coarse-grained and fine-grained levels, such as pie charts, line charts, and bar charts. The application's functionality was demonstrated in practice based on three datasets from three OTA websites, which were analyzed and evaluated based on several matrices, namely, the precision, recall, and F1-score. The results revealed that the performance for the F1-score was 0.95 ± 0.03, 0.87 ± 0.02, and 0.92 ± 0.07 for document-level sentiment analysis, aspect-level sentiment analysis, and aspect-polarity detection, respectively. The developed application (Sentilytics 1.0) can analyze sentiment at document and aspect levels. The two levels of sentiment analysis are based on two models generated by fine-tuning CNN and LSTM models using specific architectures and domain data (Indonesian hotel reviews).

Product reviews on the marketplace are interesting to research. Aspect-based sentiment analysis (ABSA) can be used to find in-depth information from a review. In one review, there can be several aspects with a polarity of sentiment. Previous research has developed ABSA, but it still has limitations in detecting aspects and sentiment classification and requires labeled data, but obtaining labeled data is very difficult. This research used a graph-based and semi-supervised approach to improve ABSA. GCN and GRN methods are used to detect aspect and opinion relationships. CNN and RNN methods are used to improve sentiment classification. A semi-supervised model was used to overcome the limitations of labeled data. The dataset used is an Indonesian-language review taken from the marketplace. A small part is labeled manually, and most are labeled automatically. The experiment results for the aspect classification by comparing the GCN and GRN methods obtained the best model using the GRN method with an F1 score = 0.97144. The experiment for sentiment classification by comparing the CNN and RNN methods obtained the best model using the CNN method with an F1 score = 0.94020. Our model can label most unlabeled data automatically and outperforms existing advanced models.