Garuda - Garba Rujukan Digital

Lexicon-Based Sentiment Analysis of Indonesian Language Student Feedback Evaluation Raginda Firdaus; Ibnu Asror; Anisa Herdiani
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.408

Student feedback for lecturer plays an important role, it used to improve the quality of lecturer in teaching. In general, student feedback consists of two types, quantitative feedback and qualitative feedback. For quantitative feedback, it can easily analyze using statistical calculations, because it contains closed questions with multiple choices. But for qualitative feedback, it is difficult to analyze, because it contains open questions with essay answers. Lecturers can analyze manually, but it takes extensive times and the results can be very subjective. To overcome this problem, sentiment analysis is applied to analyze textual data automatically in order to improve teaching evaluations. This research uses student feedback as dataset, and lexicon approach with InSet Lexicon. In this research, the evaluation result shows that system accuracy is 90.9%.

Implementation of Naïve Bayes and Gini Index for Spam Email Classification Fikri Rozan Imadudin; Danang Triantoro Murdiansyah; Adiwijaya
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.452

Email is a medium of information that is still frequently used by people today. At the moment email still has an endless problem that is spam email. Spam email is an email that can pollute, damage or disturb the recipient. In this study, we show the performance and accuracy of Multinomial Naïve Bayes (MNNB) and Complete Gini-Index Text (GIT) for use in spam email filtering. In this study, we used 6 cross-validations as testers for the built classification machines. We found that the average yield can exceed Multinomial Naïve Bayes without using feature selection which only uses 80000 features with a difference of 0.39%. Feature selection also increases speed during classification and can reduce features that are less relevant to the category to be classified.

Analysis and Implementation of Signature Based Method and Structure File Based Method for File Carving Anjar Afrizal; Niken Dwi Wahyu Cahyani; Erwid Musthofa Jadied
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.457

File Carving is a data recovery technique based on file structure and content without relying on filesystem information or metadata. The problem in carving files is its high false positive value especially when the file is fragmented (either linear fragmented or non-linear fragmented). The aim of this study is to implement and analyze the performance of two file carving method (Signature Based and File Structure Based) as a solution to the problem of the carving process. By focusing on JPEG, GIF and PNG files, two datasets are used, namely: CFReDS Project (NIST Project) and Basic Data Carving Test (Nick Mikus Project). The analysis is based on the recovery performance (carving recall, supported recall, carving precision), execution time, and memory usage. From the recovery performance parameter, the File Structure Based method gets a higher overall value than the Signature Based method. However, based on the execution time performance parameter, the Signature Based method has better execution time and use fewer resources compared to the File Structure Based method.

Implementation of Analytical Hierarchy Process (AHP) for Determining Priority of Software Assessment in West Java Provincial Government Based on ISO/IEC 25010 (Case Study: Sapawarga Application) Nisrina Nurhuda; Eko Darwiyanto; Sri Widowati
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.525

The quality of the software is defined ISO as the totality of the features and characteristics of the product or services that depend on the ability to satisfy user needs. Sapawarga is software used to meet the needs of citizens in channeling aspirations, proposals, and obtaining information in one application. There are some negative comments about the app on Google’s app store. This indicates there are quality issues in sapawarga software. The results of a follow-up survey showed users of the application experienced a 45.20% decrease, due to the server not responding, difficulty finding information, etc. This research was conducted to evaluate the quality of the software based on ISO 25010 consisting of eight characteristics including functional suitability, reliability, usability, performance efficiency, maintainability, portability, security, and compatibility. The AHP pairing comparison method is used to select the three most important ISO characteristics. These three most important characteristics are then used to assess the application of sapawarga and propose recommendations for improvement. Based on expert judgment using AHP pair comparison method, the three characteristics that most affect the application of sapawarga are functional suitability, usability, and performance efficiency with interest rates of 24.9%, 23.2%, 16.5%.

The Implementation of f(x) = 3(x 3 − x 2 − x) + 2 as CSPRNG Chaos-Based Random Number Generator Maria Rosalina Yopeng; Alz Danny Wowor
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.546

This research implemented the cubic function f(x) = 3(x^3 − x^2 − x) + 2 using a FixedPoint Iteration to produce several iteration functions that can be used as random number generator. The test results obtain six iteration functions, and based on graphic visualizationwith Scatter plot and randomness test with mono bit test, bit block, and run test, the results only obtain two iteration functions namely x2 − 1 + 2/(3x) and f(x) = 1 + 1/x − 2/(3x^2)which can produce CSPRNG Chaos-based random number. Encryption testing shows that both functions can generate keys that make plaintext and ciphertext statistically unrelated, so the f(x) = 1 + 1/x − 2/(3x^2) function can be used as a CSPNRG chaos-based random number generator function.

Implementation of K-Means++ Algorithm for Store Customers Segmentation Using Neo4J Arief Chaerudin; Danang Triantoro Murdiansyah; Mahmud Imrona
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.547

In the era of data and information, data has become one of the most useful and desirable things. Data can be useful information if the data is processed properly. One example of the results of data processing in business is by making customer segmentation. Customer segmentation is useful for identifying and filtering customers according to certain categories. Analysis of the resulting segmentation can produce information about more effective target market, more efficient budget, more accurate marketing or promotion strategies, and much more. Since segmentation aims to separate customers into several categories or clusters, a clustering algorithm can be used. In this research, customer segmentation is carried out based on the value of income and value of expenditure. The categorization method that will be used for this research is to use the K-Means ++ algorithm which is useful for determining clusters of the given data. In this study, the implementation of K-Means ++ is carried out using Neo4J. Then in this research, a comparison of K-Means ++ and K-Means is carried out. The result obtained in this study is that K-Means ++ has a better cluster than K-Means in term of silhouette score parameter.

Analysis of Website Portal Rumah Belajar Using WebQual 4.0 Method and Important Performance Analysis ADE BAYU SEPTIAN; Eko Darwiyanto; Hetti Hidayati
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.548

Portal Rumah Belajar is implementing E-Government in Presidential Instruction No. 3 of 2003 concerning National Development Policy and Strategy. The government is required to take advantage of advances in information and communication technology by developing e-government-based public services. The Portal Rumah Belajar is a means for students to get various information about the learning material. Therefore this website must be able to present quality information based on user perceptions. Based on previous research that analyzed the Rumah Belajar website, there are deficiencies in usability factors and information quality factors that affect user satisfaction. Therefore, the study discusses the Portal Rumah Belajar Website Analysis topic using the WEBQUAL 4.0 method and Importance Performance Analysis to evaluate the Portal Rumah Belajar website's quality. WEBQUAL 4.0 as a reference for making a questionnaire and Importance Performance Analysis as an analysis in the form of a level of conformity to the gap quantification. The results obtained from the evaluation that the website's quality has a conformity level of 101.16% concluded that the user feels satisfied with the site's service. The gap level has a positive value of 0.04. It can be concluded that users experience satisfaction with the website

The Quality Comparison of WebRTC and SIP Audio and Video Communications with PSNR Muhhamad Affan Hasby; Aji Gautama Putrada; Febri Dawani
Indonesia Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.549

Video and audio communications have become part of all areas of work. Two real-timecommunication protocols commonly used for IP-based video and audio communicationsare Session Initiation Protocol (SIP) and real-time web communications (WebRTC). Bothprotocols have been widely used in softphone and video conferencing applications. Themain objective of this research is to make an analysis of the performance of a client serverapplication for video and audio communications developed by SIP and WebRTC. The SIPsystem consists of a softphone on the client side using Bria and a FreePBX server, forWebRTCapplications, using JavaScript and a server at Node.js. The results showed that the WebRTCaudio and video communication provided better quality in terms of PSNR. This is due tothe different codecs used between WebRTC and SIP. WebRTC uses VP8 as video codec, SIPuses H.246 as video codec, WebRTC uses G.711 as audio codec, and implemented SIP usesG.729 as audio codec.

Lexicon-Based Sentiment Analysis of Indonesian Language Student Feedback Evaluation Firdaus, Raginda; Asror, Ibnu; Herdiani, Anisa
Indonesian Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.408

Student feedback for lecturer plays an important role, it used to improve the quality of lecturer in teaching. In general, student feedback consists of two types, quantitative feedback and qualitative feedback. For quantitative feedback, it can easily analyze using statistical calculations, because it contains closed questions with multiple choices. But for qualitative feedback, it is difficult to analyze, because it contains open questions with essay answers. Lecturers can analyze manually, but it takes extensive times and the results can be very subjective. To overcome this problem, sentiment analysis is applied to analyze textual data automatically in order to improve teaching evaluations. This research uses student feedback as dataset, and lexicon approach with InSet Lexicon. In this research, the evaluation result shows that system accuracy is 90.9%.

Implementation of NaÃ¯ve Bayes and Gini Index for Spam Email Classification Imadudin, Fikri Rozan; Murdiansyah, Danang Triantoro; Adiwijaya
Indonesian Journal on Computing (Indo-JC) Vol. 6 No. 1 (2021): April, 2021
Publisher : School of Computing, Telkom University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34818/INDOJC.2021.6.1.452

Email is a medium of information that is still frequently used by people today. At the moment email still has an endless problem that is spam email. Spam email is an email that can pollute, damage or disturb the recipient. In this study, we show the performance and accuracy of Multinomial NaÃ¯ve Bayes (MNNB) and Complete Gini-Index Text (GIT) for use in spam email filtering. In this study, we used 6 cross-validations as testers for the built classification machines. We found that the average yield can exceed Multinomial NaÃ¯ve Bayes without using feature selection which only uses 80000 features with a difference of 0.39%. Feature selection also increases speed during classification and can reduce features that are less relevant to the category to be classified.

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota bandung,

Jawa barat

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email -

Phone -

Journal Mail Official -

Editorial Address -

Location Kota bandung, Jawa barat INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota bandung,

Jawa barat

INDONESIA