Skripsi
AUTOMATIC TEXT SUMMARIZATION PADA TEXT BERITA MENGGUNAKAN METODE TEXTRANK
Advances in information technology have enabled easy access to news through online platforms. However, to find information about a news story, it takes a lot of time for readers to read the entire content in text form. One way to get information and understand the content of the news is by reading the summary. Text summarization is the process of presenting the core information of a text without losing its importance. In this research, text summarization on news using the TextRank method. Tests conducted using test data as much as 50 news texts. The process starts from the preprocessing stage, word weighting with Word2Vec, applying the TextRank algorithm, and calculating the evaluation value of the summary results. In preprocessing, data processing is carried out which includes case folding, tokenization, stopword removal, and stemming. Next, summarize using the TextRank method, then the results of the system summary and manual summary will be evaluated with the ROUGE metric with precision, recall, and f-measure values. The use of precision to measure the accuracy of information selection, recall measures the ability to capture all important information, and f-measure provides an overall picture of the quality of the summary. Based on the evaluation results obtained, ROUGE-1 (unigram) achieved an average precision value of 40.01%, recall 54.47%, and f-measure 47.99%, while ROUGE-2 (bigram) achieved an average precision value of 63%, recall 68.06%, and f-measure 62.97%.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407000837 | T139203 | T1392032024 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available