網路文字探勘運用於電信業客戶流失的研究

Web Mining for Customers Churn Analysis in Telecommunication Industries

何文峰(Wen-Feng Ho)

指導教授 ： 邱昭彰

元智大學/資訊學院/資訊管理學系/碩士(2007年)

https://doi.org/10.6838/YZU.2007.00127

摘要

走過網際網路dot com泡沫化，隨著Web 2.0的興起，網際網路正在展現其創造價值最大的潛力，那就是它提供了更有效的資訊傳播方式。這樣的趨勢，產生了所謂的CGM (Consumer-Generated Media)。這也強化了「口碑傳播」(口耳相傳)的深度和廣度，尤其是負面口碑。所以企業有監控、追蹤CGM訊息的必要性。但網路上的CGM訊息，呈爆炸性的成長，在執行上需耗費很大的人力成本。所以本研究運用Crawler依據時間及關鍵字參數，來抓取與追蹤CGM的資訊，藉此節省企業的成本也避免人為的疏忽。取回之文章資料，則運用關鍵詞擷取技術，讓企業的高階主管，能很快的對取回之文章內容有一個初步的概念。期許本研究能協助企業掌握CGM資訊、瞭解消費者趨勢、進行危機管控。

關鍵字

網站探勘 ； 網路蜘蛛

並列摘要

After burst of the internet network dot com bubble, Web 2.0 becomes popular. Internet network is representing the greatest potentiality of its creation value, that is - it offers more effective way of information dissemination. This trend brings the CGM (Consumer-Generated Media ), and it makes WOM (Word of Mouth) more powerful. So, enterprises have to control and track the CGM information. But CGM message at the network shows explosive growth. So this research uses Crawler to retrieve and track the information of CGM according to time and key word parameter and by using this, it saves the cost of enterprises and avoids the artificial carelessness. We use text mining technology of key information extraction to let high-level managers of enterprise can have a figure of information . Expect this research can help enterprises to grasp CGM information, understand consumer's trend and control the crisis.

並列關鍵字

Web Mining ； Crawler

參考文獻

3. Arndt, & Johan A., “Role of Product-Related Conversations in the Diffusion of a New Product,” Journal of Marketing Research, Vol. 4, No. 3, pp. 291-295, 1967.

5. Bansal, H. S. & Voyer, P. A., “Word-of-mouth processes within a services purchase decision context,” Journal of Service Research, Vol. 3, No. 2, pp. 166-177, 2000.

6. Bickart, B. and R. M. Schindler, “Internet Forums As Influential Sources of Consumer Information,” Journal of Interactive Marketing, Vol. 15, No. 3, pp. 31-40, 2001.

10. Chakrabarti, S., "Data mining for hypertext: A tutorial survey," ACM SIGKDD Explorations, Vol. 1, No. 2, pp. 1-11, 2000.

11. Chen, K. J. and S. H. Kiu, “Word identification for Mandarin Chinese sentences,” Fifth International Conference on Computational Linguistics, pp. 101-107, 1992.