187-586-1-CE (2)

2y ago
11 Views
2 Downloads
2.03 MB
17 Pages
Last View : 1m ago
Last Download : 2m ago
Upload by : Macey Ridenour
Transcription

1/16/2021Editorial TeamHOMEABOUTUSER HOMESEARCHCURRENTARCHIVESANNOUNCEMENTSHome About the Journal Editorial TeamINDEXINGEditorial TeamPeer-ReviewersEditorial TeamFocus & ScopeAuthor GuidelinesEditor-in-ChiefHeri Nurdiyanto, Scopus ID: 57200089726 STMIK Dharma Wacana, IndonesiaAssociate EditorsDr Md Ataul Islam, Scopus ID: 7403693279, University of Manchester, United KingdomDr Zeena N. Al-kateeb, Scopus ID: 57216253357, University of Mosul, IraqLeonel Hernandez, SCOPUS ID: 57193734233, Institución Universitaria ITSA, Colombia, ColombiaDr. Osamah Ibrahim Khalaf, Scopus ID:56009431000 Al-Nahrain University - College of Information Engineering, Baghdad, Iraq., IraqNidal A.M Jabari, Scopus ID: 55569448900, Technical Colleges(Arroub), , PalestineDr Mazin Abed Mohammed, Scopus ID: 57192089894, University of Anbar, IraqAji Prasetya Wibawa, Scopus ID : 56012410400; Dept Electrical Engineering, State University of Malang, Malang, IndonesiaDina Fitria Murad, Scopus id : 57193666780 Bina Nusantara University, IndonesiaHiba Zuhair Zeydan, Scopus ID: 56466006400 Al-Nahrain University, IraqAndri Pranolo, SCOPUS ID : 56572821900, Universitas Ahmad Dahlan, IndonesiaDr. Arun Kumar singh, Scopus ID: 57200827321; Saudi Electronic University, Saudi ArabiaHaviluddin Haviluddin, Scopus ID: 56596793000; Departement Ilmu Komputer; Universitas Mulawarman, IndonesiaMohamed Hamada, Scopus ID: 8365771800, Dept. of Computer Science, The University of Aizu, Aizu (JAPAN)Abideen Ismail, Department of Computer Engineering, University of Maiduguri, NigeriaPradeep Kumar Atrey, Scopus ID: 6603382021, Dept. of Applied Computer Science, The University of Winnipeg (CANADA)Mustakim Mustakim, SCOPUS ID: 57195383688; Computer Science; UIN Sultan Syarif Kasim Riau, IndonesiaPublication EthicsOnline SubmissionJournal FeeScopus Citation AnalysisTEMPLATEEditorial BoardDr. Sérgio Duarte Correia, SCOPUS ID: 9335755600 Instituto Politécnico de Portalegre, PortugalSnježana Dubovicki, Scopus ID: 55274166900 Josip Juraj Strossmayer University of Osijek, CroatiaPHAM DUY NHAN, Scopus ID: 57208800189, Memorial University of Newfoundland, CanadaMd. Solaiman Mia, Scopus ID: 57150719400 Department of Computer Science and Engineering, Green University of Bangladesh, BangladeshShahab Wahhab Kareem, Scopus ID: 57205541046 Information System Engineering, Erbil Polytechnic University, IraqL. J. Muhammad, Scopus ID : 57208611115 Federal University, Kashere, Gombe State, NigeriaDr. Ramesh Kumarasamy, Scopus ID: 57210711669 Karpagam Academy of Higher Education, coimbatore, IndiaJehad A.H Hammad, Scopus ID: 572014499394. Al-Quds Open University, Palestine, Palestinian Territory, OccupiedYessi Jusman, Department of Electrical Engineering, Faculty of Engineering, Universitas Muhammadiyah Yogyakarta, Indonesia, IndonesiaGaurav Gupta, Scopus ID: 57194214351 Shoolini University of Biotechnology and Management Sciences, IndiaIswanto Iswanto, Scopus ID : 56596730700 Universitas Muhammadiyah Yogyakarta, IndonesiaDahlan Abdullah, Scopus ID: 57205132023; Department of Informatics Universitas Malikussaleh, Aceh, Indonesia, IndonesiaJoko Sutopo, Scopus ID: 57191886933, Universitas Teknologi Yogyakarta, IndonesiaAgung Budi P, UTeM Universiti Teknikal Malaysia Melaka, MalaysiaEngel Jeremias Lewi Engel, Scopus ID: 55901905700 Institut Teknologi Harapan Bangsa, IndonesiaDanny Kurnianto, Institut Teknologi Telkom Purwokerto, IndonesiaCopy EditorG Prabhakar, Scopus ID : 56711035100 V.S.B. Engineering College, Karur, Tamilnadu, IndiaMuhammad Irwanto, Scopus ID : 36608262100, Universiti Malaysia Perlis, MalaysiaMufadhol Mufadhol, Scopus ID : 57194073576 Departement of Computer System, STEKOM Semarang, IndonesiaTenia Wahyuningrum, Scopus ID : 57190841874 Institut Teknologi Telematika Telkom Purwokerto, IndonesiaAndysah Putra Utama Siahaan, Scopus ID 57191433036 Universitas Pembangunan Panca Budi,Medan IndonesiaSINTA RANKUSERYou are logged in as.swpmanMy ProfileLog OutJOURNAL CONTENTSearchInternational Journal Of Artificial Intelligence ResearchOrganized by: Departemen Teknik Informatika STMIK Dharma WacanaPublished by: STMIK Dharma WacanaJl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampungphone. 62725-7850671Fax. 62725-7850671Email: info@ijair.id internationaljournalair@gmail.com herinurdiyanto@ieee.orgSearch ScopeAllSearchBrowseBy IssueBy AuthorBy TitleView IJAIR StatcounterFONT SIZEIJAIR is licensed under a Creative Commons Attribution-ShareAlike 4.0 International t/editorialTeam1/2

1/16/2021Editorial TeamNOTIFICATIONSViewManageISSN BARCODEISSN Online 2579-7298KEYWORDSAES Algorithm Adaptive BackgroundLearning Background Subtraction BusinessDataMining Dependable Flow, Perceptron,Intelligence ClassificationBackpropagation, Citarum, Rainfall-runoffDigital Signature, Cloud Storage, Motivation,Fuzzy C-MeansMachine Learning MovementPrediction Spermatozoa classificationCovid-19algorithm cloud computing data sharingencryption feature selection melanomadetection preprocessing image systematicliterature rialTeam2/2

1/16/2021Vol 5, No 1 (2021)HOMEABOUTUSER orial TeamHome Archives Vol 5, No 1 (2021)Peer-ReviewersVol 5, No 1 (2021)Focus & ScopeArticles in pressAuthor GuidelinesPublication EthicsDOI: https://doi.org/10.29099/ijair.v5i1The following articles have been reviewed and declared accepted for publication but are in the final editing process and are awaiting publication. The title,abstract, author's name, and bibliography for each article are subject to change before publication. Articles will not be published until final evidence is validatedby their authors.Online SubmissionJournal FeeScopus Citation AnalysisTable of ContentsArticlesStochastic Perturbations on Low-Rank Hyperspectral Data for Image ClassificationAlex Sumarsono, (California State University, East Bay United States)Farnaz Ganjeizadeh, (California State University, East Bay )Ryan Tomasi, (California State University, East Bay )10.29099/ijair.v5i1.196Abstract views : 29 Abstract views : 30Fuzzy C-Means Clustering Algorithm For Grouping Health Care Centers On Diarrhea DiseaseAhmad Chusyairi, (Universitas Bina Insani Indonesia)Pelsri Ramadar Noor Saputra, (STIKOM PGRI Banyuwangi Indonesia)Efendi Zaenudin, (Department of Bioinformatics and Medical Engineering, Asia University, Taichung Taiwan, Province of China)10.29099/ijair.v5i1.191Abstract views : 93Uplift modeling VS conventional predictive model: A reliable machine learning model to solve employeeturnoverDavin Wijaya, (Universitas Prima Indonesia Indonesia)Jumri Habbeyb DS, (Universitas Prima Indonesia Indonesia)Samuelta Barus, (Universitas Prima Indonesia Indonesia)Beriman Pasaribu, (Universitas Prima Indonesia Indonesia)Loredana Ioana Sirbu, (The University of Florence Italy)Abdi Dharma, (Universitas Prima Indonesia Indonesia)10.29099/ijair.v4i2.169USERYou are logged in as.swpmanMy ProfileLog OutAbstract views : 46Analysis of Expert System for Early Diagnosis of Disorders During Pregnancy Using the Forward ChainingMethodBasiroh Basiroh, (Teknik Informatika, Universitas Nahdlatul Ulama Al Ghazali Indonesia)Shahab Wahhab Kareem, (Information System Engineering, Erbil Polytechnic University Iraq)Heri Nurdiyanto, (STMIK Dharma Wacana Indonesia)10.29099/ijair.v5i1.203SINTA RANKAbstract views : 30Covid-19: Implementation e-voting Blockchain ConceptMustofa Kamil, (Universitas Pendidikan Indonesia Indonesia)Ankur Singh Bist, (Graphic Era Hill University India)Untung Rahardja, (Universitas Raharja Indonesia)Nuke Puji Lestari Santoso, (Universitas Raharja Indonesia)Muhammad Iqbal, (Universitas Raharja Indonesia)10.29099/ijair.v5i1.173TEMPLATEPDF views : 4Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Features and Fuzzy CMeansI Made Suwija Putra, (Department of Information Technology, Faculty of Engineering, Udayana University, Bali Indonesia)Yonatan Adiwinata, (Department of Information Technology, Faculty of Engineering, Udayana University, Bali Indonesia)Desy Purnami Singgih Putri, (Graduate School of Department of Electrical Engineering and Computer Science, Kanazawa University Japan)Ni Putu Sutramiani, (Department of Information Technology, Faculty of Engineering, Udayana University, Bali Indonesia)10.29099/ijair.v5i1.187PDF1 - 12Abstract views : 41JOURNAL CONTENTSearchSearch ScopeAllSearchBrowseBy IssueBy AuthorBy TitleFONT SIZECausal Relations of Factors Representing the Elderly Independence in Doing Activities of Daily Livings UsingS3C-Latent AlgorithmChristantie Effendy, (Departement of Medical Surgical Nursing, Faculty of Medicine, Public Health, and Nursing, University Gadjah MadahIndonesia)Nurhaeka Tou, (Universitas Islam Indonesia Indonesia)Ridho Rahmadi, (Universitas Islam Indonesia Indonesia)10.29099/ijair.v5i1.206TOOLSAbstract views : 19Intelligent Traffic Monitoring Systems: Vehicle Type Classification Using Support Vector MachineIka Candradewi, (Universitas Gadjah Mada Indonesia)Agus Harjoko, (Universitas Gadjah Mada Indonesia)Bakhtiar Alldino Ardi Sumbodo, (Universitas Gadjah Mada Indonesia)10.29099/ijair.v5i1.201Abstract views : 23International Journal Of Artificial Intelligence w/131/2

1/16/2021gVol 5, No 1 (2021)Organized by: Departemen Teknik Informatika STMIK Dharma WacanaPublished by: STMIK Dharma WacanaJl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampungphone. 62725-7850671Fax. 62725-7850671Email: info@ijair.id internationaljournalair@gmail.com herinurdiyanto@ieee.orgNOTIFICATIONSView IJAIR StatcounterCURRENT ISSUEViewManageIJAIR is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.ISSN BARCODEISSN Online 2579-7298KEYWORDSAES Algorithm Adaptive BackgroundLearning Background Subtraction BusinessDataMining Dependable Flow, Perceptron,Intelligence ClassificationBackpropagation, Citarum, Rainfall-runoffDigital Signature, Cloud Storage, Motivation,Fuzzy C-MeansMachine Learning MovementPrediction Spermatozoa classificationCovid-19algorithm cloud computing data sharingencryption feature selection melanomadetection preprocessing image systematicliterature 132/2

International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xxISSN: 2579-72981Extractive Text Summarization of Student Essay AssignmentUsing Sentence Weight Features and Fuzzy C-MeansI Made Suwija Putraa,1,*, Yonatan Adiwinataa,2, Desy Purnami Singgih Putrib,3, Ni Putu Sutramiania,4a Department of Information Technology, Faculty of Engineering, Udayana University, BaliSchool of Department of Electrical Engineering and Computer Science, Kanazawa University, Kanazawa,Japan1 putrasuwija@unud.ac.id*; 2 natanzt1@gmail.com; 3 desysinggihputri@stu.kanazawa-u.ac.jp; 3 sutramiani@unud.ac.id* corresponding authorb GraduateARTICLE INFOABSTRACTArticle history:Received: August 3, 2020Revised: October 11, 2020Accepted: October 24, 2020One of the main tasks of a lecturer is to give students an academicassessment in the learning process. The assessment process beginswith reading or checking the answers of student assignments thatcontain a combination of very long sentences such as essay orreport assignments. This certainly takes a lot of time to get theprimary information contained therein. It is necessary to summarizethe answers so that the lecturer does not need to read the wholedocument but is still able to take the essence of the response to thetask. This study proposes the application of summarizing textdocuments of student essay assignments automatically using theFuzzy C-Means method with the sentence weighting feature. Thesentence weighting feature is used by selecting the sentence withthe highest weight in one cluster, helping the system to get theprimary information from a document quickly. The results of thisstudy indicate that the system succeeds in summarizing text with anaverage evaluation of the values of precision, recall, accuracy, andF-measure of 0.52, 0.54, 0.70, and 0.52, respectively.Keywords:Text SummarizationEssay AssignmentsWeight SentencesFuzzy C-MeansCopyright 2021 International Journal of Artificial Intelligence Research.All rights reserved.IntroductionThe rapid development of information technology makes a massive increase in the number ofdigital texts. According to MGI research [1] that in 2010, people in the world stored more than 6exabytes of digital text data on devices such as personal computers (PCs), notebooks, and mobilephones. Digital text is text in digital format in the form of a representation of the binary alphabet[2]. It can be found in article documents, news, books, scientific papers, or student assignmentscollected online. These documents often contain long text, so it requires time to filter theinformation in it. One example, it takes a lot of time for lecturers to give a proper assessment ofstudent essay assignment documents. This because they have to read all the documents to get thecore information. Text summarization becomes one of the quick and appropriate solutions to findthe core sentences of the essay document so that it can speed up the assessment process.Summarizing the text is to condense it into a shorter version while maintaining the primaryinformation and its overall meaning. It is challenging to summarize large text documents manually[3]. Therefore, this study proposes an automatic digital text summarization system to summarizestudent essay assignment documents and display essential sentences. This study uses thetechnique of extracting materials extensively with the Fuzzy C-Means method, which is to givesentence weight in each sentence the student answers.The Fuzzy C-Means method, developed by Dunn in 1973 and improved by Bezdek in 1981, isoften used in pattern recognition [4]. Fuzzy C-Means can make each object a member of a clusterDOI: 10.29099/ijair.v5i1.187W : http://ijair.id E : info@ijair.id

2International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xxISSN: 2579-7298of several choices smoothly, able to group extensive data, more robust against outlier data, andeffective and efficient. Besides that, it is simple and easy to implement [5]–[8].Previous studies on summarizing documents used as a basis for this research include Research[9], which implements Fuzzy C-Means to summarize English-language journal documents. Theapplication created can summarize with input pdf format text. Sentence weighting uses the TF IDFmethod.Research [10] developed a text summarization system model consisting of four stages. Thepreprocessing step changes the unstructured text into the structured one.Other research [11] proposed the topic of sentence-based Bayes models to summarizedocuments using terms and associations. An efficient variational Bayesian algorithm is derived forestimating model parameters. Experimental results on benchmark data sets indicate theeffectiveness of the proposed model for multi-document summarizing tasks.Other studies [12] propose making automatic document summaries using word features andthe K-Means method. Automatic document summaries can be used to get text summaries quickly,making it easier for users to get the primary information from a document. This study summarizesdocuments using word features and the K-Means method.Previous studies generally use documents such as articles and news which have no multi-topiccontent and use different languages. As for materials such as essay assignment documents orstudent scientific papers consisting of several questions and answers, at this time, the summarizinghas not been done much. Based on these reasons, research on the automatic summarizing of textsfor student essay assignment documents using the Fuzzy C-Means method and weightingsentences (TF ISF) be raised. This research used the data from the assignment of the UdayanaUniversity Department of Information Technology students. All of the data are in Indonesian.MethodResearch on Extractive Text Summarization of Student Essay Assignment Using SentenceWeight Features and Fuzzy C-Means has the following initial stages: (1) Conduct a literature studyon the concept of summarization and the Fuzzy C-Means method; (2) The collection of test datasourced from digital texts of student essay assignments collected through e-learning systems; (3)Preparation of test data before processing by the system includes data acquisition, data cleaningand conversion of file formats to .txt.After these stages are carried out, the next step is to design the system flow design andimplement the plan. Fig. 1 shows the flow of the system starting from the text of the document tobe summarized; of course, it has been through the stage of preparing test data. In the next step,the test data enters the summarization system that begins with indexing, which is the process offinding all the features in the text, both word features, punctuation features, numeric features, andothers in the document.Furthermore, this study has two main processes, namely the summarization process and theresults of the summarization evaluation process. The Summarization with extractive method hasthree general procedure steps, as below[13][14]Step 1: The first step is making a document representation. Preprocessing techniquesperformed in this level, including tokenization, stop word removal, stemming, sentence separation,frequency calculation, and others.Step 2: The sentence assessment is being done in this step. Three approaches are followed: Weighting of words to determine which are the important words by using the TF-IDFmethod Weighting of sentences such as verifying sentence features (their position in the document,similarity to titles, sentences containing important words) by using the TS-ISF method.I Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

ISSN: 2579-7298 International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xx3Graph scoring to analyze the relationships between sentences.Step 3: In this step, the sentences are sorted, then take the highest score as the final summaryin a single documentThe Summarization Process on this study as presented in Fig. 2 has several stages, such asIndexing, Clustering Process with Fuzzy C-Means, and Sentence Weighting in Clusters. The systemevaluation process is comparing results from the summary of the system with the manual reviewby the expert.Fig. 1 Overview system of Extractive Text Summarization of Student Essay Assignment Using SentenceWeight Features and Fuzzy C-MeansA. IndexationThe indexing process starts from inputting the .txt file as text to be summarized into the system.This process begins by separating each sentence. Separation of sentences is done by using severalindicators such as periods (.), Exclamation points (!), And question marks (?). Examples ofdifficulties encountered are the use of period punctuation (.), it is not only used when ending asentence but also used to abbreviate names and others. In this process, case folding is carried outto change all the letters into a uniform form. In this study, all words uniformed in lower cases.Furthermore, words are taken in each sentence (tokenization) and discard the words that are thewords that appear most often but do not have significant meaning (stop word). The list of stopwords taken from the Indonesian stop words database. Next is the stemming process, which is theprocess of removing affixes to get essential words in Indonesian. This system uses a library fromSastrawi [15].B. Clustering Sentences with Fuzzy-C-Means MethodThe sentence clustering process is needed to organize extensive data collections by partitioningseveral data sets automatically, so objects that have similarities will be grouped into a group that isdifferent from other groups [5][16].The results of the preprocessing stage are used to form clusters that contain sentences whosefeatures are close together. Basically, the Fuzzy C-Means (FCM) algorithm has a lot in common withK-Means. The output of FCM is not a fuzzy inference system, but a row of cluster centers andseveral membership degrees for each data point [17]. The FCM grouping procedure is as follows:1. Define the following parameters.a. Number of clusters c (adjusted according to the level ofsummarization)b. Powers of number wc. MaxIter Maximum iterationd. Error threshold valueI Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

4International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xxe. Initial objective function P0 0f. t 1Initial iterationISSN: 2579-72982. Initialize the membership data as matrix form, X, with the size of n x m (n number of datasamples, m data attributes), where Xij index of data sample (i 1,2, , n) and attributes (j 1,2, ,m). The membership value derived from the frequency of words in each sentence.3. Generating random values from 0 to 1 for each member of the group, μik, i 1,2, ,n; k 1,2, ,c; as an elements of initial partition matrix u. μik. Calculate the total number of eachcolumn (attribute) with the following formula:(1)Qj is degrees of membership per column 1 with j 1,2, m, then calculate with thefollowing formula:(2)4. Calculate the centroids of k: Vkj, with k 1,2, ,c; and j 1,2, ,m and value of μik fromformula 2.(3)5. Calculate the value of the objective function in the t iteration, Pt. The objective function isused to get the right cluster center. It means the cluster of data in last iteration wasachieved.(4)i 1,2, ,n; k 1,2, ,m6. Calculate the difference of membership level for each data in partition matrix:(5)with: i 1,2, n; and k 1,2,.c.7. Iteration end if the difference of objective function value less than the Error threshold value( Pt – Pt-1 ) or the number of iterations has passed the maximum iteration limit (t MaxIter). If the above condition not met, t t 1 and repeat to step 4.C. Sentence Weighting with TS-ISFTerm frequency weighting - inverse sentence frequency (TF-ISF) done after getting all theiteration process completed. Before searching for the TF-ISF value, the word weight value must befound using the TF-IDF method [17]. This method is a numerical value to represent howI Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

ISSN: 2579-72985International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xximportance the words is in the whole document.TF shows word frequency in documents. IDF is ameasure to reduce the weight of words that often appear in the corpus and increase the weight ofwords that rarely occur.At this stage, the TF-ISF value of each sentence will be added up and used as the value of asentence, which will be used at the sentence selection stage in each cluster. The ISF and TF-ISFequations can be seen in the following equations number 1 and 2 [18]:(1)(2)With TFt,s is the frequency of occurrence of the word t in the sentence s, N is the number ofsentences in the document, and ISFt is the number of sentences containing the word t. The TFISFt,svalue, s, will be high if the word t appears several times in a sentence and rarely appears in anothersentence, and low if the word t appears almost in the entire sentence [19].The final stage of the summarization process is to take the sentence that has the highestsentence weight for each cluster. The number of sentences taken as a result of summarizationdepends on the selected concise level value, which starts from 10% -50%. For example, if there are20 sentences in the text tested with a summarization rate of 40%, the system will create 8 clusters(the user selected), then one sentence which is the closest to its center will be taken from eachcluster.Fig. 2 Algorithm of the text summarization system using the Fuzzy C-Means method and weighting ofsentencesD. System Evaluation TechniquesThe process carried out in the system evaluation stage is to compare the results ofsummarization by the system with the manual version. There are several evaluation techniques inmeasuring the quality of the sentence grouping model, including information matrix,misclassification index, purity, f-measure [20]. This study uses the F-Measure Technique in order toI Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

6International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xxISSN: 2579-7298get the value of accuracy, precision, and recall, and f-measure of the summary results issued by thesystem, this is used as an indicator of the results of this research. The flow of the system evaluationprocess in this study is shown in Fig. 3.Fig. 3 System evaluation process flowchartThe f-measure measurement is based on the precision and recall values obtained. Theconcepts of recall and precision can be seen in Table 1 below.Table 1 The concept of counting recall and precisionRetrievedNot RetrievedRelevanttpfnNon-RelevantfptnThe recall is the proportion of sentences rediscovered as a summary, and precision is theproportion of the number of sentences found and considered relevant [21]. From Table 1, theformula for calculating recall, precision, accuracy, and f-measure values described as follows.(3)(4)(5)(6)True positive (tp) is a sentence that is in the expert summary and appears in the system summary.False positives (fp) sentences that are not in the expert summary but appear in the systemsummary. False-negative (fn) is a sentence that is in the expert summary but does not appear inthe system summary. And true negative (tn) is a sentence that is not in the experts and systemsummary.Result and DiscussionThe summarization system for student essay assignment documents automatically uses theFuzzy C-Means method built using the Python programming language with WX packet as thesystem interface. The overall process interface of this system can be seen in Fig. 4.I Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

ISSN: 2579-7298International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xx7Fig. 4 Genaral System interface of the summarization system for student essay assignment documentsautomatically uses the Fuzzy C-MeansA. Test Data CollectionThe document test data used in this study was obtained from student assignments collected inthe e-learning system (ELSE U) at Udayana University in 2019. Document collection is done bydownloading randomly without regard to any indicators. The student essay document wasachieved from 10 student in the e-learning system with the same assignment topic.The entire document was selected by looking at the length of the students answers to make itmore reliable when tested. The selection process gives ten documents, which are then convertedmanually by copy-pasting each sentence in the PDF document in accordance with the rules thathave been made into a .txt format file.This collection process takes a long time because each sentence must be checked and adjustedto the rules that have been made i.e., a collection of sentences must be complete, more than threesentences in 1 paragraph, and not a sentence that explains the tables, pictures or formulaequations. The results of the conversion resulted in an average of 113 words omitted in eachdocument. The comparison of the number of words after and before the conversion can be seen inFig. 5 below.Fig. 5. Change in the number of words when converting test documents to .txt format. The x-axis is thedocument number, the y-axis is the number of wordsI Made Suwija Putra et.al (Extractive Text Summarization of Student Essay Assignment Using Sentence Weight Featuresand Fuzzy C-Means)

8International Journal of Artificial Intelligence ResearchVol 5, No 1, 2021, pp. xx-xxISSN: 2579-7298As shown in Fig. 5, the average of reduction from 10 document is 6,87%. The deleted wordssuch as the non-standard word and word that describe objects, pictures, tables and equations orformulas because these words are not reliable. So, the remaining 93.13% of the document contentis included in the process of converting documents or test data. Test data also used as a manualsummarization material conducted by experts to be used as a comparison with the results of asummary of the system to carry out the evaluation process. In this study, it assumed that theresults of the manual review are good. Fig. 6 shown the result of testing data that was processedby format conversion and word reduction as mention before.Fig. 6 Example of testing data that converted to .txt formatFrom 10 documents that have been converted, paragraphs that have a minimum 4 sentencesare selected, so that each n cluster produced by the Fuzzy C-Means clustering process can be filledwith correct members, that will have selected 1 sentence for every 1 cluster[22]. Fuzzy C-Meansclustering is also useful for researcher to create variations for ideal extractive summaries [23].From the process of taking this paragraph, it produces 105 text which will be the test data to beprocessed in testing the automatic text summarization system using this Fuzzy C-Means method.B. Implementation of Text SummarizationSystem implementation is the stage after carrying out the system design process to completethe system to be ready for use and test functionality is done to make sure the algorithm of Fuzzy CMeans with the TF-ISF sentence weighting can produce clusters containing representing sentencesto become a summary based on the summary level chosen. This

Dr Mazin Abed Mohammed , Scopus ID: 57192089894, University of Anbar, Iraq Aji Prasetya Wibawa , Scopus ID : 56012410400; Dept Electrical Engineering, State University of Malang, Malang, Indonesia Dina Fitria Murad , Scopus id : 57193666780 Bina Nusantara University, Indonesia Hiba Zuhair Zeydan , Scopus ID: 56466006400 Al-Nahrain University, Iraq

Related Documents:

Linda Pavlovski Juanita Velasquez Stephanie Williams 586-256-1005 586-256-1280 586-256-1968 586-243-9496 586-256-2044 586-744-8940 DETROIT . Pamela Walker 231-357-3087 231-342-5006 231-342-2454 231-357-5352 YPSILANTI Counties: Washtenaw Mailing Ad

SEMCA (800) 686-6543 Silver Heights Opioid Rehab - Armada (586) 210-4829 Substance Abuse Hotline (800) 662-4357 Urgent Care Beaumont Urgent Care (586) 884-2727 Clinton Urgent Care Walk In Clinic (586) 267-1334 Lakeside Urgent Care - Clinton Twp (586) 412-0890 Maplecrest Urgent Care-Sterling Heights, MI (586) 795-2980

What is one reason to use IBM Forms over FileNet eForms within the context of an ICM Solution? A. IBM Forms is more tightly integrated with ICM. C2070-586 VCE Dumps C2070-586 Exam Questions C2070-586 Braindumps 2 / 6. . B. IBM Cognos RTM C. IBM WebSphere ILOG JRules D. IBM

UP6S-25 125 18 25 98 547 1,203 145 18 25 92 547 1,203 200 18 25 75 547 1,203 UP6S-30 125 22 30 117 586 1,290 145 22 30 112 586 1,290 200 22 30 92 586 1,290 Mounting Options Nominal Power Dimensions (Length x Width x Height) Additional Mass kW hp mm in kg lb Integrated Drye

Apr 14, 2019 · Warren, MI 48091 Phone: 586-755-1313 Fax: 586-690-4441 Sick Call: 586-755-5490 Email: ologparish2012@gmail.com Parish Staff/Ban Điều Hành GX. Rev. Hoằng Lâm/Pastor-Lm. Chánh xứ Dcn. (Phó Tế), Kevin Tietz/DRE Trưởng Giáo Lý Ron Frankland/Office Manager-Thư Ký Regina Ciavattone, Vicariate Rep.

Richmond Lenox EMS 34505 32 Mile, Richmond 48062 (586) 727-2184 www.lenoxtwp.org Employment/ Internships Baker College of Clinton Twp 34950 Little Mack, Clinton Twp. 48035 (586) 791-3000 www.baker.edu Entertainment Richmond Community Choir 9750 Division, Columbus 48063 (586) 727-8584 www.rich

Isaac Monfort El- ementary Phone: (586) 797-5700 Attendance Line: 586 797-5799 Fax: (586) 797-5701 Monfort Elementary School Is A State and National Blue Ribbon School The Staff Of Monfort Elementary Is Committed To Working Together So That Students Know They Are Valued and Will Learn Our Essential Curriculum. November 2016 Dear Parents:

GREER COMPANY Crane Systems GREER Company 1918 East Glenwood Place Santa Ana CA 92705 Page 1 of 44 MicroGuard 586 Operation/Setup Manual W458200 REV C 10/29/02 MicroGuard 586 Rated Capacity Indicator/Limiter System Operation/Setup Manual OK DISPLAY SETUP SETUP CODE STOP RATED CAPACITY MG-586! SELECT CONTRAST