博碩士論文 945202041 完整後設資料紀錄

DC 欄位 語言
DC.contributor資訊工程學系zh_TW
DC.creator陳正揚zh_TW
DC.creatorCheng-Yang Chenen_US
dc.date.accessioned2007-10-10T07:39:07Z
dc.date.available2007-10-10T07:39:07Z
dc.date.issued2007
dc.identifier.urihttp://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=945202041
dc.contributor.department資訊工程學系zh_TW
DC.description國立中央大學zh_TW
DC.descriptionNational Central Universityen_US
dc.description.abstract在最近幾年的研究當中,關於網頁內容的研究數量相當的多。對於網站上的意見分析也顯得越來越重要。人們在網路上對於某個產品的評價對於我們在網路上購物或者下決策時是相當重要的參考依據。舉例來說,一個在網路上的使用者在選擇要入住哪家旅館時,通常會透過參考入口網站中有關於使用者想比較的旅館的意見來做為決定的因素。因此,在本篇論文當中,我們使用了自然語言處理以及資料探勘中的技巧來分析入口網站中的網頁並擷取出有關於擷取的網頁的旅館的特徵,並將每一個特徵透過搜尋引擎來計算特徵的分數。並且設計了一個線上的系統,讓使用者可以透過我們的介面來做比較。相信透過這樣的方式,使用者在比較網頁中大量的意見時可以更清楚、簡單、直覺的比較並更快速的做出決定。zh_TW
dc.description.abstractIn recent years, a considerable of number of studies have been conducted on the effects of comments on the web. People’s appraisal has high confidence to express their behaviors and aspects. Thus, the appraisals on the web are significant information for customer making their decision. For instance, people could select the best hotel according to the existing appraisals on the web. In this paper, we are concerned with the difference between reviews of products. An unsupervised learning approach can model this information perfectly. Furthermore, we simply combined the data mining with natural language processing techniques to extract features from a large of appraisals. For each feature, we generalized a corresponding appraisal by using probabilistic measure and we designed a web interface to let user compare online. We adopted the Hotel information that was collected form Yahoo as our dataset. Lastly, our comparative results were clearly represented in a visual way.en_US
DC.subject資料探勘zh_TW
DC.subject意見擷取zh_TW
DC.subject語意分析zh_TW
DC.subjectdata miningen_US
DC.subjectsentiment classificationen_US
DC.subjectopinino extractionen_US
DC.title網頁意見特徵評價化之應用於旅館比較zh_TW
dc.language.isozh-TWzh-TW
DC.titleFeature Appraisal for Hotel Comparsionen_US
DC.type博碩士論文zh_TW
DC.typethesisen_US
DC.publisherNational Central Universityen_US

若有論文相關問題,請聯絡國立中央大學圖書館推廣服務組 TEL:(03)422-7151轉57407,或E-mail聯絡  - 隱私權政策聲明