Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Ilmiah Kursor

COMPARISON OF STEMMING AND SIMILARITY ALGORITHMS IN INDONESIAN TRANSLATED AL-QUR'AN TEXT SEARCH Ika Oktavia Suzanti; Achmad Jauhari
Jurnal Ilmiah Kursor Vol 11 No 2 (2021)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v11i2.280

Abstract

The long history of information retrieval did not begin with Internet. Prior to widespread public daily use of search engines, in the 1960s information retrieval systems were discovered in commercial and intelligence applications. There are two stages in Information Retrieval in doing its main job which is to preprocessing text and to calculate similarity between term (word) and query (keyword) user searched for in a document. Stemming is final stage of pre-processing in an information retrieval system. The way stemming works is to remove affixes from a word, in form of prefixes, suffixes and insertions into form of basic word. Thus, in this paper we did compare search on information retrieval system without using stemming algorithm, using stemming Porter, Nazief & Adriani and Enhanced Confix Stripping with similarity method used is cosine similarity and dice similarity. Based on test results, text search ability on dice similarity is faster in stemming process with Porter Stemmer and ECS algorithms. While in Nazief & Adriani algorithm and without stemming, cosine similarity is faster than dice similarity.
PCA-counseled k-means and k-medoids with dimension reduction for improved in determining optimal aid clustering Jauhari, Achmad; Suzanti, Ika Oktavia; Anamisa, Devie Rosa; Admojo, Fadhila Tangguh
Jurnal Ilmiah Kursor Vol. 13 No. 1 (2025)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v13i1.460

Abstract

Assuring effective allocation requires targeted distribution of aid, which makes aid clustering a crucial component. For the purpose of using data-driven segmentation based on important characteristics to determine effective help targeting, accuracy in clustering is essential. The study explores the combination of Principal ComponentAnalysis (PCA), k-means, and k-medoids to enhance aid clusters, with the goal ofincreasing aid distribution accuracy and efficiency. The information gathered consists of 1600 records with 13 attributes. In order to standardized the data having two processes in it, preprocessing is first applied. When used with PCA, it makes measuring variance easier and preserves 80% of the variation by choosing five components. Thenumber of clusters may be determined with the use of PCA, k-medoids, and the k-means approach. Greater PCA-k-means silhouette coefficients, which indicate betterclustering ability, are highlighted by comparative analysis. This analysis shows thatPCA-k-means is an effective technique for creating accurate and unique clusters withina data set's structure.The clustering results using the PCA-k-means algorithm have produced the greatest accuracy in the silhouette score of 0.49 and the DBI score is 0.84.