Generally, Online Travel Agent (OTA) has a review element where clients can give reviews of the facilities they have used. Availability huge volume makes it troublesome for service executives to know percent that an effect on their services. Thus, is essential develop sentiment assessment technique with respect hotel reviews, particularly in Indonesian language. This research use Long-Short Term Memory (LSTM) model as well Word2Vec model. The integration and LSTM variables used this are...

Hand-crafted features engineering is a labor-intensive and highly-cost task. In this paper, we implement Word2Vec as an alternative solution of hand-crafted for sentiment analysis hotel reviews in the Indonesian language. To obtain highest performance analysis, evaluate three parameters include model architecture, evaluation method, vector dimension. This process was implemented towards our proposed corpus specific domain, i.e. reviews, consists 2500 language (1250 positive 1250 negative...

The tourism industry is one of foreign exchange sector, which has considerable potential development in Indonesia. Compared to other Southeast Asia countries such as Malaysia with 18 million tourists and Singapore 20 tourists, Indonesia the largest Asia's country have failed attract higher tourist numbers compared its regional peers. only managed 8,8 2013, value each year likely decrease. Apart from infrastructure problems, marketing managing also form obstacles for growth. An evaluation...

Sentiment analysis is a field of study that analyzes sentiment. One method for doing sentiment Latent Dirichlet Allocation (LDA) extracts the topic documents where represented as appearance words with different probability. Therefore, we need data representation in visual form easier to understand than text and tables. visualization wordcloud provides frequency. This research will perform from students' comments toward university, this case Universitas Diponegoro, using LDA polarity...

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 the coarse-grained document to fine-grained aspect level./Methodology/Approach: There are four main stages study: development of sentiment analysis model at level based on convolutional neural network (CNN), improved long short-term memory (LSTM), deployment for multilevel application, its performance evaluation. The...

Scene classification based on latent Dirichlet allocation (LDA) is a more general modeling method known as bag of visual words, in which the construction vocabulary crucial quantization process to ensure success classification. A framework developed using following new aspects: Gaussian mixture clustering for process, use an integrated (IVV), built union all centroids obtained from separate each class, and usage some features, including edge orientation histogram, CIELab color moments,...

Accreditation is one of the quality measurements for a University. Some elements these are students and graduate students. Prevention to drop out problem that considered very important university itself. High levels will have bad impact on university, such as reputation or low-grade accreditation. This research presenting results case study analysis in educational data, by analyzing data using mining technique. The author classification method, focuses drop-out prediction undergraduate...

The Family Hope Program (PKH) is a conditional cash transfer initiative in Indonesia aimed at reducing poverty and improving access to education, health, welfare services among Beneficiary Families (KPM). Despite its success, ensuring that KPM achieve independence prosperity remains key challenge. This study examines the strategic management practices of Ministry Social Affairs promoting self-reliance KPM. Using qualitative descriptive approach, data were collected through literature...

Traffic accidents caused by seat belt violations remain a severe problem in low-income countries. Identifying the vehicles of these violators is vital for enhancing safety. Therefore, this research develops vehicle license plate detection and recognition system to support problem. The proposed was divided into three subsystems: windshield detection, character recognition. subsystem used You Only Look Once (YOLOv11) model. License combined determination Region Of Interest (ROI) YOLOv11....

The comments received on Internet-based online hotel reservation services are an important resource that can be utilised by service providers including managers' and hoteliers' for exercising quality control measures in their service. Importantly this contributes towards increased customer satisfaction revisits. In study, Sentiment Analysis (SA) is used to analyse the from customers. However, there several problems associated with SA such as unequal number of each class data (imbalanced...

A massive number of news articles leads to the potential problem in automatic classification task. The discussions on English have been widely studied. However, it is contrast Indonesian articles. method that has implemented limited conventional methods, such as Naïve Bayes and Support Vector Machine. Both methods rigid classify a document into one topic. Therefore, we implement Topic Modeling which represent distribution topics topic represented by set words. Latent Dirichlet Allocation....

Product reviews on the marketplace are interesting to research. Aspect-based sentiment analysis (ABSA) can be used find in-depth information from a review. In one review, there several aspects with polarity of sentiment. Previous research has developed ABSA, but it still limitations in detecting and classification requires labeled data, obtaining data is very difficult. This graph-based semi-supervised approach improve ABSA. GCN GRN methods detect aspect opinion relationships. CNN RNN...

Abstract. Error typing resulting in the change of standard words into non-standard are often caused by misspelling. This can be addressed developing a system to identify errors typing. Approximate string matching is one method that widely implemented error using several search algorithms, i.e. Levenshtein Distance, Hamming Damerau Distance and Jaro Winkler Distance. However, there no study compares performance four algorithms. Therefore, this research aims compare between algorithms order...

Quercitrin is the main component that can be isolated from parasitic plant Dendrophthoe falcata and exhibits high antioxidant activity.The purpose of this study to make a quercitrin nanoemulsion formulation test its activity.This research method uses spontaneous emulsion.Quercitrin formulated by emulsion with addition oil, tween 80 as surfactant, phosphate buffer pH 7.0 water phase at low temperatures.Quercitrin products are further characterized which include particle size, polydispersity...

Population growth and changes in public consumption patterns cause increases the volume, types characteristics of waste. This increase requires waste management effort. One efforts that can be performed is by separating into several types. Upon separation, proceeded to recycling process. Current technological advances have supported automatic sorting so process easier faster do. research proposes image classification support using Support Vector Machine (SVM) algorithm SIFT-PCA (Scale...

The contents of online news documents are almost the same that will lead to redundancy or called yellow journalism. Yellow journalism can make it difficult for readers distinguish containing fact opinionated information. Therefore, is necessary extend more research about multi-document summarization so easily understand intent documents. Latent Dirichlet Allocation (LDA) - Significance Sentences one methods summarization, which performs better than term frequency algorithm. However, document...

The mangrove ecosystem is crucial for addressing climate change and supporting marine life. To preserve this ecosystem, understanding community awareness essential. While latent Dirichlet allocation (LDA) commonly used this, it has drawbacks such as high resource requirements an inability to capture semantic nuances. We propose a technique using Sentence-BERT K-Means Clustering topic identification, these drawbacks. Analyzing mangrove-related Twitter data in Indonesian from 1 September 2021...

Currently, there are a large number of hotel reviews on the Internet that need to be evaluated turn data into practicable information. Deep learning has excellent capabilities for recognizing this type data. With advances in deep paradigms, many algorithms have been developed can used sentiment analysis tasks. In study, we aim compare performance classical machine algorithms—logistic regression (LR), naïve Bayes (NB), and support vector (SVM) using Word2Vec model conjunction with such as...

The use of IoT-based applications to retrieve data in relatively real-time has increased significantly. One the is weather monitoring application called Rendeng (Rapid Envelopment Data Sending). aim this not only collect data, but also present information as user's needs. Rendeng, developed for specific user characteristic, four different education backgrounds, which are: Informatics, Mathematics, Statistics, and Physics. Therefore, there a need test usability order gain value efficiency,...

User ratings on products sold bye-commerce greatly influence the number of purchases. Positive will encourage other buyers to participate in buying product. While negative given by users reduce interest purchasing products. Nonconformities between rating and user reviews sometimes provide a wrong assessment This happens because also quality delivery services from e-commerce. Based that issue, utilization Latent Dirichlet Allocation (LDA) could be used sentiment analysis reviews. Sentiment...

Stunting is a condition in which children experience impaired growth and development, caused by malnutrition, repeated infections, inadequate psychosocial stimulation. It often remains unrecognized due to lack of awareness the community. Therefore, first step towards developing solution for stunting understand level sentiment community issues related stunting. As online media are widely used everyday life, they offer significant potential providing such an understanding. However, exploiting...

Advances in information technology have given rise to online hotel reservation options. The user review feature is an important factor during the booking of hotels. Generally, most service providers provide and rating features for assessing However, not all or recap reviews every aspect services offered. Therefore, we propose a method summarise based on multiple aspects, including food, room, service, location. This uses long short-term memory (LSTM), together with hidden layers automation...

Traveloka provides a space for its users to write reviews about their hotel reservation services. These are very useful in informing managers of the level customer satisfaction. Sentiment analysis is tool that can be used analyse such determine whether they express opinions or not, so satisfaction measured based on number sentiments (positive negative) contained opinions. In this research, Naïve Bayes classifier was perform hierarchical sentence sentiment obtained from Traveloka. addition,...