Sentiment Analysis on KAI Twitter Post Using Multiclass Support Vector Machine (SVM)

2023

bits

The era of digital transformation has sparked innovations in product and service marketing strategies in various sectors, one of which is the tourism sector. In the hospitality industry context, product marketing using website-based digital media allows consumers as hotel guests to review the products and services received. The Tripadvisor website is a digital marketing platform that provides review features for app users, especially consumers, to give ratings and reviews. This study aims to analyze the quality of hotel services using the Service Quality (SERVQUAL) framework based on the results of the classification of hotel guest sentiment data using the Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM) algorithm by the stages of the Cross-Industry Standard Process for Data Mining (CRISP-DM). The CRISP-DM framework consists of six stages, namely: business understanding stage, data understanding stage, data preparation stage, modeling stage, evaluation stage, and deployment stage. The SERVQUAL framework consists of several dimensions: reliability dimension; responsiveness; assurance; empathy; tangibles. The review data that will be processed is the consumer review data of The Oberoi Beach Resort Lombok; Sheraton Senggigi Beach Resort; Sudamala Resort Sengiggi; Holiday Resort Lombok; Aston Sunset Beach Resort. The results of this study show that the SVM algorithm performs better than NBC, where the accuracy value is 98.57%, the precision value is 100%, the recall value is 97.14%, and the f-measure value is 98.54%. The AUC value is 100%, and the t-Test value is 98.6%. Unlike the case with the results of SVM's algorithm performance evaluation without using the SMOTE Upgrading Operator, where the accuracy value is 95.71%, the precision value is 95.71%, the recall value is 100%, and the f-measure value is 97.81%. In addition, the AUC value is 91.1%, and the t-Test value is 95.7%.

Section: Algoritma Support Vector Machineunclassified

Analisis Sentimen Wisatawan terhadap Kualitas Layanan Hotel dan Resort di Lombok Menggunakan SERVQUAL dan CRISP-DM

2023

bits

“…Support Vector Machine (SVM) merupakan salah satu algoritma yang dapat digunakan untuk klasifikasi data menggunakan hyperplane [33]. Karim menjelaskan bahwa konsep SVM menitikberatkan pada risk minimization, yaitu estimasi fungsi dengan cara meminimalisir batas dari generalization error, sehingga SVM mampu mengatasi overfitting [34].…”

Section: Algoritma Support Vector Machineunclassified

Analisis Sentimen Konsumen terhadap Food, Services, and Value di Restoran dan Rumah Makan Populer Kota Makassar Berdasarkan Rekomendasi Tripadvisor Menggunakan Metode CRISP-DM dan SERVQUAL

2023

bits

Culinary is one of the economic activities that support national economic growth and represents the gastronomy of the archipelago in Indonesia. Culinary tourism activities have become famous for domestic and foreign tourists to experience the taste of a food based on the culture of each region. Makassar is one of the regions with diverse types of food and beverages and has a relationship with local socio-cultural values. Considering this, this study aims to analyze consumer sentiment toward food and services in ten restaurants in Makassar based on the recommendations of the Tripadvisor website using the Cross-Industry Standard Process for Data Mining (CRISPD-DM) and Service Quality (SERVQUAL) methods. The stages of CRISP-DM are as follows: the stage of understanding business processes; the stage of understanding data; the stage of preparing data; the modeling stage; the evaluation stage; and the deployment stage. The algorithms used as models are k-Nearest Neighbor (kNN), Naïve Bayes Classifier (NBC), Decision Tree (DT), and Support Vector Machine (SVM). The results of this study show that the DT algorithm when using the SMOTE operator where the resulting accuracy value is 93.25%, precision is 88.74%, recall is 99.10%, and f-measure is 93.62%. In addition, the k-NN algorithm without using the SMOTE operator showed an accuracy value of 98.72%, a precision of 98.72%, a recall of 100%, and an f-measure of 99.36%. However, the resulting AUC value is 0.905 (90.5%). Meanwhile, when using the SMOTE operator, the SVM algorithm produces an accuracy value of 99.42%, a precision of 100%, a recall of 98.84%, and an f-measure of 99.42%. Meanwhile, the resulting AUC value is 1,000 (100%). Based on the ROC value, three algorithms can be used as models in the CRISPP-DM and SERVQUAL frameworks: the k-NN algorithm without SMOTE and the DT and SVM algorithms using the SMOTE operator

“…Support Vector Machine (SVM) merupakan salah satu algoritma yang dapat digunakan untuk klasifikasi data menggunakan hyperplane [20]. Karim menjelaskan bahwa konsep SVM menitikberatkan pada risk minimization, yaitu estimasi fungsi dengan cara meminimalisir batas dari generalization error, sehingga SVM mampu mengatasi overfitting [21].…”

Section: Algoritma Support Vector Machineunclassified

Analisis Performa Algoritma NBC, DT, SVM dalam Klasifikasi Data Ulasan Pengunjung Candi Borobudur Berbasis CRISP-DM

2022

bits

The approach of visitor sentiment analysis to Borobudur Temple tourist destinations in Indonesia can be classified using various algorithms to get optimal results. Good algorithm performance can be seen from the confusion matrix (accuracy, precision, recall) value, Area Under Curve (AUC) value, and Receiver Operating Characteristic (ROC). This study used the Naïve Bayes Classifier (NBC), Decision Tree (DT), and Support Vector Machine (SVM) algorithms against 3850 text data obtained from the Tripadvisor website, especially reviews of Borobudur Temple visitors. The method refers to the Cross-Industry Standard Process for Data Mining (CRISP-DM) for optimizing tourist destination products and services by paying attention to six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The results of this study show that the results of NBC's algorithm performance evaluation can be seen to have a change in the confusion matrix value at the accuracy value from 98.73% to 95.6%, the precision value changed from 98.72% to 98.97%, the recall value also changed from 100% to 96.54%. In addition, the Area Under Curve (AUC) of NBC also changed from 0.500 (50%) to 0.693 (69.35%). In addition, the results of the DT algorithm performance evaluation showed a change in the confusion matrix value at the accuracy value from 97.55% to 94.40%, the precision value increased from 97.63% to 91.86%, the recall value also changed from 99.90% to 99.47%. The Area Under Curve (AUC) of DT value also changed from 0.591 (59.1%) to 0.932 (93.2%). The results of the SVM algorithm performance evaluation showed a change in the confusion matrix value at the accuracy value from 98.73% to 99.41%; the precision value changed from 98.72% to 100%, and the recall value also changed from 100% to 99.01%. The Area Under Curve (AUC) of the SVM value also changed from 0.961 (96.1%) to 1.00 (100%). In addition, the T-test results show that the SVM algorithm is more dominant compared to other algorithms, where the SVM algorithm T-test value is 0.994 compared to the DT algorithm T-test value of 0.944 and the NBC algorithm T-test value of 0.98. Based on the Receiver Operating Characteristic (ROC) value, it can be seen that the DT algorithm also shows good performance in addition to SVM. It indicates that in analyzing the sentiment of visitors to Borobudur Temple, the best-recommended algorithm is the Support Vector Machine