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.

Website technology have created both opportunities and challenges for higher education. Information systems as online learning medium need to pay attention to access, quality and user needs in order to improve the quality of e-learning services. The research objective is to determine user acceptance of the system. The service quality method as identification in solving problems. The research focus on the analysis of five dimensions namely measurable, reliability, responsiveness, assurance and empathy. The research was conducted at the research college at Muria Kudus University. The results state that the assessment model of a system on the website can be completed properly. The level of effectiveness is carried out with respondents as users through the distribution of questionnaires. The results of the analysis with a statistical correlation performance test of 0.985 were declared accepted with a validity level of 97% indicating that the success of the system implemented was from the acceptance side. The higher the empathy with service quality and performance expectations, the greater the student's intention to receive online education services. This research is a reference for developing information systems on e-learning.

The information systems success strategy contributes to understanding of digitalization. This research aims to evaluate user satisfaction with the e-learning system continuously. The research method is hybrid, combining constructs of a unified theory of acceptance and use of technology, the technology acceptance model, and service quality (SVQ). Data collection was conducted through the distribution of questionnaires targeting instructors. Data analysis utilized structural equation modeling with partial least squares. This method was used to test the measurement model with factor loadings and average variance extracted (AVE) above 0.5. Meanwhile, validity testing on cross-loading had indicator values for each variable higher than other variables, with composite reliability above 0.7. These results were supported by hypothesis testing, which indicated that website quality positively influences user satisfaction, leading to sustained intention. The original sample obtained a value of 0.633; mean of 0.624; standard deviation of 0.105, and a p-value below 0.01. Additionally, user subjective norms have a strong relationship between sustained intention and system appropriateness, of 0.763 in using e-learning.

Wooden or bamboo fences, commonly used for coastal protection, have limited effectiveness in reducing wave height due to their porous structure, which provides only moderate wave damping. To address this issue, our study proposes a modification that retains these fences while strategically incorporating submerged rocks, similar to gabions, to exploit friction and achieve significant wave height reduction. We employed a mathematical model based on modified Shallow Water Equations to investigate the wave attenuation. A key measure, the wave transmission coefficient ($K_t$), for quantifying wave height reduction was determined using both analytical and numerical methods. The numerical $K_t$ obtained from simulations was $0.2831$, whereas the analytically computed $K_t$ value was $0.2622$, which indicates a reduction of over 70% in the initial wave amplitude due to the combined effect of submerged rocks and wooden fences. These results, which align closely with experimental data, validate the credibility of our approach. A detailed sensitivity analysis illustrates the effectiveness of both wooden fences and submerged rocks in attenuating wave height, which depends on structure dimensions and friction coefficients. Optimization studies present various optimal structures, underscoring the critical role of the structure’s friction coefficient in minimizing the wave transmission coefficient, and recommend the use of rough materials for optimal wave height reduction. In summary, our paper offers a robust exploration of an innovative coastal protection strategy that integrates wooden fences and rocks. The validated model, supported by analytical, numerical, and experimental evidence, has the potential to provide practical insights for coastal engineers seeking efficient wave attenuation solutions.