Garuda - Garba Rujukan Digital

Sentiment analysis on myindihome user reviews using support vector machine and naÃ¯ve bayes classifier method Hakim, Sulton Nur; Putra, Andika Julianto; Khasanah, Annisa Uswatun
International Journal of Industrial Optimization Vol 2, No 2 (2021)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijio.v2i2.4437

In the era of globalization, the internet has become a human need in doing various things. Many internet users are an opportunity for internet service providers, PT Telekomunikasi Indonesia (Telkom). One of PT Telkom's products is IndiHome. As the only state-owned enterprise engaged in telecommunications, PT Telkom is expected to meet the needs of the Indonesian people. However, based on the rating obtained by IndiHome products through the myIndiHome application on Google Play, it is 3.5 out of 87,000 more reviews. The reviews focus on how important the effect of word-of-mouth is on choosing and using internet provider products. The review data was collected on November 1, 2020 to December 15, 2020, with a total of 2,539 reviews as a sample. Â The sentiment analysis process that has been carried out shows that the number of reviews included in the negative sentiment class was 1.160 reviews, and the positive class was 1.374 reviews out of a total of 2,539 reviews. The results indicate that service errors in IndiHome services are still quite high, reaching 46.7% as indicated by the number of negative reviews. The classification results show that the average value of the total accuracy of the Support Vector Machine (SVM) method is 86.54% greater than NaÃ¯ve Bayes Classifier (NBC) method which has an average total accuracy of 84.69%. Â Based on fishbone diagram analysis, there are 12nd problems on negative reviews that classify problems 5P factors: Price, People, Process, Place, and Product.

Simulated annealing algorithm for solving the capacitated vehicle routing problem: a case study of pharmaceutical distribution Anak Agung Ngurah Perwira Redi; Fiki Rohmatul Maula; Fairuz Kumari; Natasha Utami Syaveyenda; Nanda Ruswandi; Annisa Uswatun Khasanah; Adji Chandra Kurniawan
Jurnal Sistem dan Manajemen Industri Vol. 4 No. 1 (2020)
Publisher : Universitas Serang Raya

This study aims to find a set of vehicles routes with the minimum total transportation time for pharmaceutical distribution at PT. XYZ in West Jakarta. The problem is modeled as the capacitated vehicle routing problem (CVRP). The CVRP is known as an NP-Hard problem. Therefore, a simulated annealing (SA) heuristic is proposed. First, the proposed SA performance is compared with the performance of the algorithm form previous studies to solve CVRP. It is shown that the proposed SA is useful in solving CVRP benchmark instances. Then, the SA algorithm is compared to a commonly used heuristic known as the nearest neighborhood heuristics for the case study dataset. The results show that the simulated Annealing and the nearest neighbor algorithm is performing well based on the percentage differences between each algorithm with the optimal solution are 0.03% and 5.50%, respectively. Thus, the simulated annealing algorithm provides a better result compared to the nearest neighbour algorithm. Furthermore, the proposed simulated annealing algorithm can find the solution as same as the exact method quite consistently. This study has shown that the simulated annealing algorithm provides an excellent solution quality for the problem.

Sentiment analysis on myindihome user reviews using support vector machine and naive bayes classifier method Sulton Nur Hakim; Andika Julianto Putra; Annisa Uswatun Khasanah
International Journal of Industrial Optimization Vol. 2 No. 2 (2021)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijio.v2i2.4437

In the era of globalization, the internet has become a human need in doing various things. Many internet users are an opportunity for internet service providers, PT Telekomunikasi Indonesia (Telkom). One of PT Telkom's products is IndiHome. As the only state-owned enterprise engaged in telecommunications, PT Telkom is expected to meet the needs of the Indonesian people. However, based on the rating obtained by IndiHome products through the myIndiHome application on Google Play, it is 3.5 out of 87,000 more reviews. The reviews focus on how important the effect of word-of-mouth is on choosing and using internet provider products. The review data was collected on November 1, 2020 to December 15, 2020, with a total of 2,539 reviews as a sample. Â The sentiment analysis process that has been carried out shows that the number of reviews included in the negative sentiment class was 1.160 reviews, and the positive class was 1.374 reviews out of a total of 2,539 reviews. The results indicate that service errors in IndiHome services are still quite high, reaching 46.7% as indicated by the number of negative reviews. The classification results show that the average value of the total accuracy of the Support Vector Machine (SVM) method is 86.54% greater than NaÃ¯ve Bayes Classifier (NBC) method which has an average total accuracy of 84.69%. Â Based on fishbone diagram analysis, there are 12nd problems on negative reviews that classify problems 5P factors: Price, People, Process, Place, and Product.

A Comparison Study: Clustering using Self-Organizing Map and K-means Algorithm Annisa Uswatun Khasanah
Performa: Media Ilmiah Teknik Industri Vol 15, No 1 (2016): PERFORMA Vol. 15 No. 1, Maret 2016
Publisher : Industrial Engineering Study Program, Faculty of Engineering, Universitas Sebelas Maret

Nowadays clustering is applied in many different scopes of study. There are many methods that have been proposed, but the most widely used is K-means algorithm. Neural network has been also usedin clustering case, and the most popular neural network method for clustering is Self-Organizing Map (SOM). Both methods recently become the most popular and powerful one. Many scholarstry to employ and compare the performance of both mehods. Many papers have been proposed to reveal which one is outperform the other. However, until now there is no exact solution. Different scholar gives different conclusion. In this study, SOM and K-means are compared using three popular data set. Percent misclassified and output visualization graphs (separately and simultaneously with PCA) are presented to verify the comparison result.

Sentiment Analysis of JNE User Perception using Naïve Bayes Classifier Algorithm Annisa Uswatun Khasanah; Adelia Febriyanti
OPSI Vol 15, No 1 (2022): ISSN 1693-2102
Publisher : Jurusan Teknik Industri Fakultas Teknologi Industri UPN "Veteran" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/opsi.v15i1.7179

The logistics industry is growing very rapidly. One of big industry in Indonesia is PT. Tiki Line Nugraha Ekakurir (JNE), which has been established for 29 years. This company has an extensive network in all cities in Indonesia, with service points of 1,500 locations. JNE has an application called my JNE on Google Play, which received more than 86,000 reviews and since December 2019 only got a rating of 2.4 stars out of a total rating of 5 stars. This study is obtained to analysis JNE user review data from Google Play. The reviews used in this study totaled 1,876 classified into positive and negative sentiment classes using the Naïve Bayes Classifier algorithm and word associations were also implemented. Classification with naïve bayes classifier with 90% training data and 10% test data had the best accuracy of 85.87%. Furthermore, for the text association, information is obtained that JNE users are talking about "send", "package", "courier", "good", "application", "fast", "service", "receive", "help", and "star". Whereas in the class of negative sentiment users often talk about "send", "package", "courier", "disappointed", "service", "service", "bad", "application", "severe", and "slow".

Enhancing Line Efficiency Performance at Assembly Line Using Ecrs-Based Line Balancing Concept Amalia Syaharani Ibnu; Annisa Uswatun Khasanah
Teknoin Vol. 28 No. 01 (2023)
Publisher : Faculty of Industrial Technology Universitas Islam Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20885/teknoin.vol28.iss1.art2

Recently Indonesian textile and garment manufacturer has experienced a problem with shop floor production. The complexities in the manufacturing process led to many problems such as the inefficiency, and thus prevented the company from achieving its target. In fact, even though the company has established the efficiency target of 80%, the production floor cannot realize it. Thus, this research aims to increase the line efficiency to reach the company’s target. At the beginning of the analysis, the efficiency of assembly line was only 51,68%. Since, this value did not meet the company’s target and was not satisfying; the concept of ECRS was applied. The purpose of this research is to simplify the method to provide better effect and process flow. Before applying the method, the fishbone diagrams were used. The factors of man, method, machine and measurement were used to describe the root cause of the losses. Thus, after applying the concept of ECRS, the efficiency level increased to 81,54%, which had met the company’s target. The assembly line will run better and smoother with the smaller possibility of bottleneck if all of the workstations have a relatively balanced workload.

Sentiment Analysis of PeduliLindungi User Using Naïve Bayes Classifier Algorithm and Support Vector Machine Rizki Rahmatullah; Jundi Nourfateha Elquthb; Fanya Nindha Al-Qurani; Annisa Uswatun Khasanah
Journal of Industrial Engineering and Halal Industries Vol. 5 No. 1 (2024): Vol. 5 No. 1 June (2024): Journal of Industrial Engineering and Halal Industrie
Publisher : Industrial Engineering Department, Faculty of Science and Engineering, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiehis.4672

The Indonesian government is attempting to track the spread of the virus by creating an application named “PeduliLindungi” to deal with the coronavirus's exponential increase in cases across the country. Because it has a feature to disclose the user's location immediately, it is envisaged that this program can reduce the transmission of viruses in monitoring. Indonesians have used the PeduliLindungi, and there are user reviews of both positive and negative experiences. Therefore, to enhance these services, an assessment is required. The text mining method can extract information from users' reviews to collect this data. This method's application additionally uses the Naive Bayes Classifier and Support Vector Machine algorithms, which analyze word associations and do a classification evaluation of the data's accuracy. Based on the two methods' calculations, the NBC algorithm's average classification accuracy was 83.81%, and the SVM algorithm was 93.84%. Following that, discoveries on words that frequently exist or are used by people are obtained through word associations in the sentiment analysis of positive or negative reviews.

Implementation of Class-Based Storage for Garment Accessories Warehouse Management Using FSN Analysis at PT. XYZ Jundi Nourfateha Elquthb; Lulu Riesta Nugroho; Annisa Uswatun Khasanah
Journal of Industrial Engineering and Halal Industries Vol. 5 No. 1 (2024): Vol. 5 No. 1 June (2024): Journal of Industrial Engineering and Halal Industrie
Publisher : Industrial Engineering Department, Faculty of Science and Engineering, UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiehis.4677

A manufacturing company has a close relationship with warehouse operations, which function as centres for storing and managing raw materials and finished products. Proper operational expertise is essential in warehouse management to ensure that all processes within the warehouse run smoothly. The warehouse is a meeting point for various raw materials with different specifications, making it highly susceptible to mismanagement. In this context, several issues have been identified in warehouse management, such as a lack of space or empty shelves, outdated data recording processes, and improper placement of raw materials. An analysis was conducted to identify accessory items in the warehouse based on their similarities using class-based storage to overcome these issues. In this study, the FSN (Fast, Slow, Non-moving) analysis method was used to determine the grouping of garment accessory items based on their production usage and movement in the warehouse. A total of 37 types of accessory items were identified, with the majority, 23 items, classified as fast-moving, indicated by a high turnover rate above 3. The remaining items were categorized as slow-moving and non-moving, with turnover rates below three due to their lower movement. The turnover rate indicates how often or quickly an item moves and is used (enters and exits the warehouse). Thus, several underlying causes of the issues hindering the distribution process in the garment accessories warehouse at PT XYZ were identified. Subsequently, several recommendations were provided for warehouse management, such as improving the layout according to item grouping and conducting regular evaluations to ensure a balanced availability of space and stock. This strategy is crucial for enhancing workers' productivity in the garment accessories warehouse.

Analysis of consumer characteristics on retail business with clustering analysis method and association rule for selling improvement strategy recommendations Khasanah, Annisa Uswatun; Baihaqie, Muhammad Rafly Qowi
OPSI Vol 17, No 1 (2024): ISSN 1693-2102
Publisher : Jurusan Teknik Industri Fakultas Teknologi Industri UPN "Veteran" Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/opsi.v17i1.11411

In the highly competitive retail industry, companies must continually innovate and develop unique business strategies to enhance their sales performance. The ABC Store, a mini market in Yogyakarta, has experienced fluctuating sales over the past year, failing to meet its targets. This study aims to analyze consumer purchasing behavior at the ABC Store and provide strategic recommendations to boost sales. The data analyzed in this study comprises three months of transaction records. The methods used include Association Rule - Market Basket Analysis (AR-MBA) with the FP-Growth algorithm and Clustering Analysis with K-Means. The clustering analysis identified four distinct customer segments: Mid-Morning Moderates, Diverse Afternoon Buyers, Evening Moderates, and High-Value Customers. Cluster 2, comprising Diverse Afternoon Buyers, was selected for AR analysis due to its relatively high transaction value and the variety of products purchased, indicating its potential to evolve into a High-Value Customers cluster. The analysis yielded 104 rules. The findings can inform marketing strategies to increase sales, including product bundling and customer loyalty programs such as a point system.In the highly competitive retail industry, companies must continually innovate and develop unique business strategies to enhance their sales performance. The ABC Store, a mini market in Yogyakarta, has experienced fluctuating sales over the past year, failing to meet its targets. This study aims to analyze consumer purchasing behavior at the ABC Store and provide strategic recommendations to boost sales. The data analyzed in this study comprises three months of transaction records. The methods used include Association Rule - Market Basket Analysis (AR-MBA) with the FP-Growth algorithm and Clustering Analysis with K-Means. The clustering analysis identified four distinct customer segments: Mid-Morning Moderates, Diverse Afternoon Buyers, Evening Moderates, and High-Value Customers. Cluster 2, comprising Diverse Afternoon Buyers, was selected for AR analysis due to its relatively high transaction value and the variety of products purchased, indicating its potential to evolve into a High-Value Customers cluster. The analysis yielded 104 rules. The findings can inform marketing strategies to increase sales, including product bundling and customer loyalty programs such as a point system.

Simulated annealing algorithm for solving the capacitated vehicle routing problem: a case study of pharmaceutical distribution Redi, Anak Agung Ngurah Perwira; Maula, Fiki Rohmatul; Kumari, Fairuz; Syaveyenda, Natasha Utami; Ruswandi, Nanda; Khasanah, Annisa Uswatun; Kurniawan, Adji Chandra
Jurnal Sistem dan Manajemen Industri Vol. 4 No. 1 (2020)
Publisher : Universitas Serang Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30656/jsmi.v4i1.2215

This study aims to find a set of vehicles routes with the minimum total transportation time for pharmaceutical distribution at PT. XYZ in West Jakarta. The problem is modeled as the capacitated vehicle routing problem (CVRP). The CVRP is known as an NP-Hard problem. Therefore, a simulated annealing (SA) heuristic is proposed. First, the proposed SA performance is compared with the performance of the algorithm form previous studies to solve CVRP. It is shown that the proposed SA is useful in solving CVRP benchmark instances. Then, the SA algorithm is compared to a commonly used heuristic known as the nearest neighborhood heuristics for the case study dataset. The results show that the simulated Annealing and the nearest neighbor algorithm is performing well based on the percentage differences between each algorithm with the optimal solution are 0.03% and 5.50%, respectively. Thus, the simulated annealing algorithm provides a better result compared to the nearest neighbour algorithm. Furthermore, the proposed simulated annealing algorithm can find the solution as same as the exact method quite consistently. This study has shown that the simulated annealing algorithm provides an excellent solution quality for the problem.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search