The more rapid and large number of electronic documents stored in University library repositories or Departments, such as scientific works from academicians including theses, research reports, etc., are available in the digital version. In the process of grouping the thesis title automatically it is hoped that it can help policy makers such as the head of the study program. In this case the researcher uses fuzzy c-means algorithm which can group data in clusters so that the data of a cluster has a high level of equality with each other. In the application there is a text mining method which is a development of data mining that can be applied to overcome thesis grouping problems or research data. The result is a web that can classify research data / thesis data with a total accuracy of 96%. This number is the accuracy given based on the performance of the fuzzy c-means algorithm on the system.
Abstrak – Skripsi merupakan penelitian akhir bagi mahasiswa strata-1. Dengan semakin bertambahnya dokumen skripsi, maka akan terbentuk informasi dari kumpulan dokumen tersebut. Penelitian ini dilakukan untuk menentukan pemodelan topik dan analisis tren topik dari kumpulan abstrak skripsi Program Studi Sastra Ingris UINSA tahun 2014 sampai 2019. Dari 720 dataset abstrak skripsi dilakukan pemodelan topik dengan metode Latent Semantic Analysis yang meliputi preprocessing, pembobotan term, dan perhitungan Singular Value Decomposition. Pemodelan Topik menghasilkan 20 topik linguistik dan 17 topik literatur. Kemudian pada analisis tren topik, diperoleh 7 tren topik untuk setiap jenis penelitian. Penelitian didominasi oleh penelitian linguistik tindak tutur yang termasuk dalam bidang sosiolinguistik. Berdasarkan hasil analisis jenis penelitian dibandingkan dengan data real jenis penelitian Program Studi Sastra Inggris UINSA, menghasilkan hasil analisis penelitian linguistik memiliki presisi 80% dan recall 90%, sedangkan jumlah penelitian literatur memiliki presisi 74% dan recall 57%, tingkat akurasi analisis jenis penelitian memiliki rata-rata 79%
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.