Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476298Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Prof. Dr. Nazlia Omar | |
| dc.contributor.author | Al-Ismaily Khalid Khalifa Juma (P63366) | |
| dc.date.accessioned | 2023-10-06T09:16:01Z | - |
| dc.date.available | 2023-10-06T09:16:01Z | - |
| dc.date.issued | 2014-06-02 | |
| dc.identifier.other | ukmvital:81482 | |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476298 | - |
| dc.description | Opinion Question Answering (Opinion QA) is the task of enabling users to explore others opinions toward a particular service of product in order to make decisions. Arabic Opinion QA is more challenging due to its complex morphology compared to other languages and has many varieties dialects. On the other hand, there are insignificant research efforts and resources available that focus on Opinion QA in Arabic. This study aims to address the difficulties of Arabic Opinion QA by proposing a hybrid method of machine learning techniques and lexicon-based approach. The machine learning techniques that have been used in this study consists of three classifiers which are Naive Bayes (NB), Support Vector Machine (SVM) and Knearest Neighbor (KNN). The proposed method contains pre-processing phases such as, transformation, normalization and tokenization and exploiting auxiliary information (thesaurus). The lexicon-based approach is executed by replacing some words with its synonyms using the domain dictionary. The classification task is performed by a classifier to classify the opinions based on the positive or negative sentiment polarity. The proposed method has been evaluated using the common information retrieval metrics i.e. Precision, Recall and F-measure. The experimental results have demonstrated that NB outperforms SVM and KNN by achieving 91% accuracy,Soal jawab pendapat adalah tugasan yang membolehkan pengguna meneroka pendapat orang lain tentang sesuatu perkhidmatan atau produk dalam membuat keputusan. Kesukaran soal jawab pendapat terhasil daripada fakta yang ia adalah kombinasi dua tugas pemprosesan bahasa tabii yang mencabar iaitu analisis sentimen dan soal jawab, berbanding aplikasi soal jawab tradisional yang mencari maklumat secara fakta terhadap soalan. Soal jawab pendapat lebih sukar kerana ia mencari pendapat sentimental pengguna ke atas sasaran yang spesifik. Selain daripada itu, tidak banyak usaha yang signifikan dilakukan dalam mengkaji soal jawab pendapat dalam bahasa Arab. Terdapat beberapa sebab mengapa soal jawab Bahasa Arab menjadi agak mencabar. Ia mempunyai morfologi kompleks berbanding bahasa lain dan ia mempunyai pelbagai dialek. Ini membawa kepada satu lagi kesukaran di mana kebanyakan penulis menyatakan persoalan dan pendapat menggunakan dialek setempat berbanding bahasa Arab yang piawai. Kajian ini adalah bertujuan untuk menangani kesukaran soal jawab pendapat di dalam Bahasa Arab dengan mengusulkan kombinasi kaedah pendekatan berasaskan leksikon dan pengelasan menggunakan Naive Bayes. Kaedah yang dicadangkan mengandungi fasa pra pemprosesan seperti transformasi, normalisasi dan tokenisasi dan mengeksploitasi maklumat tesaurus. Hasil eksperimen telah menunjukkan ketepatan sebanyak 91%. Hasil kajian ini menunjukkan keputusan yang menggalakkan dalam bidang soal jawab pendapat.,Master | |
| dc.language.iso | eng | |
| dc.publisher | UKM, Bangi | |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
| dc.rights | UKM | |
| dc.subject | Arabic Opinion QA | |
| dc.subject | Difficulties | |
| dc.subject | Lexicon-based approach | |
| dc.subject | Hybrid method of machine learning techniques | |
| dc.subject | Semantic computing. | |
| dc.title | A hybrid of machine learning techniques and lexicon-based approach for Arabic opinion question answering | |
| dc.type | theses | |
| dc.format.pages | 81 | |
| dc.identifier.callno | QA76.5913 .I837 2014 3 | |
| dc.identifier.barcode | 001681 | |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_81482+SOURCE1+SOURCE1.0.PDF Restricted Access | 1.39 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.