Putri, Chandra Ayu Anindya (2018) Query Expansion Pada LINE TODAY Dengan Algoritme Extended Rocchio Relevance Feedback. Sarjana thesis, Universitas Brawijaya.
Abstract
LINE TODAY memberikan akses informasi berupa konten-konten berita up to date. Data pada LINE TODAY dimanfaatkan untuk dapat dilakukan fitur pencarian berita. Teknik Query Expansion akan sangat berguna jika dikombinasikan dengan sistem pencarian, sebab query yang diinputkan pengguna akan dikombinasi dengan query tambahan yang diberikan oleh sistem. Query tambahan akan membuat query yang pengguna hasilkan lebih spesifik. Selain itu, hadirnya feedback pengguna (user judgement/explicit relevance feedback) yang melakukan penilaian pada tiap berita akan meminimalisir query yang ambigu. Proses yang dilakukan diawali dengan teknik preprocessing, yang terdiri dari beberapa tahapan, yaitu cleansing, case folding, tokenization, filtering, hingga stemming. Kemudian dilakukan pembobotan term (term weighting) dan cosine similarity. Setelah itu, proses yang dilakukan ialah perhitungan dengan metode Extended Rocchio Relevance Feedback yang merupakan metode turunan dari Rocchio Relevance Feedback, untuk menghasilkan query tambahan. Hasil yang diperoleh berdasarkan dari implementasi maupun pengujian pada penelitian Query Expansion pada LINE TODAY dengan Algoritme Extended Rocchio Relevance Feedback menghasilkan rata-rata nilai Precision sebesar 0.53308, Recall sebesar 0.81708, F-Measure sebesar 0.59553, dan Akurasi sebesar 0.9574. Nilai akurasi yang dida pat dengan metode Extended Rocchio Relevance Feedback berdasar user judgement cenderung meningkat hingga 2% dibandingkan pencarian otomatis dengan metode Rocchio Relevance Feedback.
English Abstract
LINE TODAY provides access to up-to-date news contents. Data on LINE TODAY are used to be able to do search engine feature. Query Expansion technique will be very useful if it is to be combined with search engine system where the queries inputted by users are combined with additional queries from the system. These additional queries will make queries generated by users more specific. In addition, users feedback (user judgement/explicit relevance feedback) assessing on each news can minimize ambiguous queries. The process begins with preprocessing technique consisting of several stages which are cleansing, case folding, tokenization, filtering, and stemming. And then, term weighting and cosine similarity. The next process is calculated using the Extended Rocchio Relevance Feedback method which is a traditional method from Rocchio Relevance Feedback to generate an additional queries. The results are obtained from implementation and testing process of Query Expansion on LINE TODAY with Extended Rocchio Relevance Feedback Algorithm resulted an average Precision value of 0.53308, Recall value of 0.81708, F-Measure value of 0.59553, and Accuracy value of 0.9574. The accuracy value obtained with Extended Rocchio Relevance Feedback method based on user judgement increase by 2% compared to automated search by the method of Rocchio Relevance Feedback.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/FTIK/2018/767/051809157 |
| Uncontrolled Keywords: | Text Mining, Query Expansion, LINE TODAY, Extended Rocchio Relevance Feedback |
| Subjects: | 300 Social sciences > 302 Social interaction > 302.3 Social interaction within groups > 302.302 85 Computer aplications |
| Divisions: | Fakultas Ilmu Komputer > Teknik Informatika |
| Depositing User: | Budi Wahyono Wahyono |
| Date Deposited: | 15 Mar 2019 01:29 |
| Last Modified: | 22 Oct 2021 04:10 |
| URI: | http://repository.ub.ac.id/id/eprint/13717 |
Preview |
Text
Chandra Ayu Anindya Putri.pdf Download (12MB) | Preview |
Actions (login required)
 |
View Item |