| DC 欄位 |
值 |
語言 |
| DC.contributor | 企業管理學系 | zh_TW |
| DC.creator | 江怡璇 | zh_TW |
| DC.creator | Yi-Hsuan Chiang | en_US |
| dc.date.accessioned | 2021-7-21T07:39:07Z | |
| dc.date.available | 2021-7-21T07:39:07Z | |
| dc.date.issued | 2021 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:88/thesis/view_etd.asp?URN=108421019 | |
| dc.contributor.department | 企業管理學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 中文摘要
隨著科技的發展，手機消費者的偏好也隨之變化快速，對於手機業者來說，如何以快速且經濟實惠的方式研究消費者偏好是很重要的。網路評論為公開資料故容易蒐集，消費者會在購物前瀏覽商品的評論，好的評論會深刻的影響消費者的購買意願。此外，評論的幫助性也是考量評論好壞的一環，當消費者認為評論有幫助時，他們會為評論點選”有幫助”，而好的評論再進行研究上是有幫助的，然而，過去的研究鮮少將此因素納入考量。本篇論文希望將評論的幫助性納入消費者偏好研究中，透過Latent Dirichlet Allocation (LDA) 從評論中取出重要的手機屬性，接著使用情感分析了解消費者對於每個屬性的滿意程度，並利用Ensemble Neural Network (ENNM) 得到之神經網路模型的權重計算每個屬性的重要度，最後依照屬性重要度的計算結果，給予手機公司相關的建議。 | zh_TW |
| dc.description.abstract | Abstract
With the advance of technology, customer preference toward cellphone changes rapidly. It is important for mobile company to analyze customer preference in a(n) economic and comprehensive way. Online reviews are public data, which is easy to collect, and contains rich information that provided by customers. Customers browse reviews before buying products. Moreover, customers consider review’s quality before reading the reviews. Reviews with good quality has great influence on customer intention to buy a product. Helpful vote is one of components for customers to examine review’s quality. People press “helpful” on the review as they think is helpful. Reviews with good quality are helpful for research. However, previous researches rarely consider this component. This paper analyzed customer preference with consideration of helpful votes. Proposed method consists of Latent Dirichlet Allocation (LDA), sentiment analysis and Ensemble Neural Network (ENNM). LDA is used for extracting key cellphone attributes. Customer satisfaction toward each attribute is analyzed by sentiment analysis. By executing ENNM, attributes importance can be calculated based on weights inside each neural network. Finally, this paper gives suggestion to mobile company based on the attribute importance calculation result. | en_US |
| DC.subject | 消費者偏好分析 | zh_TW |
| DC.subject | 線上評論 | zh_TW |
| DC.subject | Latent Dirichlet Allocation (LDA) | zh_TW |
| DC.subject | 情感分析 | zh_TW |
| DC.subject | Ensemble Neural Network (ENNM) | zh_TW |
| DC.subject | Customer preference analysis | en_US |
| DC.subject | Online reviews | en_US |
| DC.subject | Latent Dirichlet Allocation (LDA) | en_US |
| DC.subject | Sentiment analysis | en_US |
| DC.subject | Ensemble Neural Network (ENNM) | en_US |
| DC.title | 線上評價分析應用於消費者偏好之研究 —以手機產業為例 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Online review analysis for customer preference in mobile industry | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |