Determination of Sentence Similarity Level Using Vector Space Model (VSM) and Word Relationship Weighting for Plagiarism Detection for Indonesian Documents

Author(s):  
Rizal Wahyudi ◽  
Muhammad Zarlis ◽  
Syahril Efendi
Author(s):  
U. L. D. N. Gunasinghe ◽  
W. A. M. De Silva ◽  
N. H. N. D. de Silva ◽  
A. S. Perera ◽  
W. A. D. Sashika ◽  
...  

Author(s):  
Jiffriya Mohamed Abdul Cader ◽  
Roshan G. Ragel ◽  
Hasindu Gamaarachchi ◽  
Akmal Jahan Mohamed Abdul Cader

Author(s):  
Anthony Anggrawan ◽  
Azhari

Information searching based on users’ query, which is hopefully able to find the documents based on users’ need, is known as Information Retrieval. This research uses Vector Space Model method in determining the similarity percentage of each student’s assignment. This research uses PHP programming and MySQL database. The finding is represented by ranking the similarity of document with query, with mean average precision value of 0,874. It shows how accurate the application with the examination done by the experts, which is gained from the evaluation with 5 queries that is compared to 25 samples of documents. If the number of counted assignments has higher similarity, thus the process of similarity counting needs more time, it depends on the assignment’s number which is submitted.


2018 ◽  
Vol 9 (2) ◽  
pp. 97-105
Author(s):  
Richard Firdaus Oeyliawan ◽  
Dennis Gunawan

Library is one of the facilities which provides information, knowledge resource, and acts as an academic helper for readers to get the information. The huge number of books which library has, usually make readers find the books with difficulty. Universitas Multimedia Nusantara uses the Senayan Library Management System (SLiMS) as the library catalogue. SLiMS has many features which help readers, but there is still no recommendation feature to help the readers finding the books which are relevant to the specific book that readers choose. The application has been developed using Vector Space Model to represent the document in vector model. The recommendation in this application is based on the similarity of the books description. Based on the testing phase using one-language sample of the relevant books, the F-Measure value gained is 55% using 0.1 as cosine similarity threshold. The books description and variety of languages affect the F-Measure value gained. Index Terms—Book Recommendation, Porter Stemmer, SLiMS Universitas Multimedia Nusantara, TF-IDF, Vector Space Model


Sign in / Sign up

Export Citation Format

Share Document