由於近十年來線上商業行為爆炸性的興起，線上購物已經顯然變為現代人們的一種主要消費型態，並且成為我們生活中不可或缺的一部分。並且在近年來，showrooming這樣的行為也同時興起。Showrooming是一種消費者去實體店面試用或是了解一樣商品後，再到線上進行購買的行為，因為線上的價格比較便宜。但不幸的是，線上那些看起來相似的產品有可能和實體店面看到的並不是相同的產品，而且根據交易糾紛的統計可以知道主要的糾紛類型還是和產品品質與產品外觀相關的問題。因此在我們無法碰觸到實體產品的情況之下，賣家的品質就成為一個我們必須考量的重要因素。更具體的來說，我們這篇論文的目標在協助使用者判斷哪些賣家可以滿足他們的需求而且同時擁有較好的品質。
根據我們對於搜尋紀錄和產品資料的觀察，拍賣網站的搜尋結果仍然是使用關鍵字搜尋技術，而我們的觀察顯示在產品的敘述和買賣雙方的問答中能夠提供消費者更多的細節來確認一個賣家是否能滿足消費者的需求。因此我們利用產品中的資訊來協助消費者尋找能夠滿足他們需求的商品。這些能夠滿足消費者需求的賣家我們會將其做為候選賣家。接著我們引入一個分類器和五項特徵值來辨識一位候選賣家是否為一個具有品質的賣家。
實驗結果則顯示擁有個人化需求的產品類別在需求和關注產品的辨識上著實較低，同時從使用特徵值的分類上也發現此類的產品，與消費者相關的特徵值反而可以有效的為這樣的類別找到合適的賣家，另外兩類個人化較低的產品類別則在採用所有特徵值的狀況下可以找到較多的合適賣家。

Due to online ecommerce has been booming for a decade. As mentioned above, shopping on the Internet has become main shopping type for modern people and one of the indispensable part in our life. And the concept of “ showrooming ” also rise in recent year. Showrooming means consumer examine products in physical store and then make their purchase online because the cheaper price. Unfortunately, the online product which looks similar may not the same product and the statistics of transactional dispute tells us the main dispute type is still about product quality and product appearance. In the situation that we can’t touch the physical product, the seller’s quality is an important factor which we should consider. More specifically, we aim at helping consumers identify which sellers can satisfy consumers’ requirement and have the better quality at the time.
According to our observation of query logs and product data, the search result of e-commerce website still use keyword match technique. The observation also showed us that the information in the product description, product question and answers between buyer and seller can provide more detail for each consumers to check whether a seller can satisfy consumers’ requirement. Therefore, we utilize the information in the product to help consumers finding the products which seller can satisfy their requirements. The sellers who can satisfy consumers will be regard as candidate sellers. And we employ a classifier and five feature to identify whether a candidate seller is a qualified seller.
The experiment result inspire that the identification rate for need and focus will be lower in the product category with individual requirement. At the same time, we find the consumer sensitive feature can make better the performance of finding qualified for the query with individual requirement when we use different feature combination. Otherwise, we classify other categories with simple requirement by all features and it will have the better result to find more qualified seller.

Reference
[1] July (2012) Support Vector Machine Guide(CSDN). Available at: http://blog.csdn.net/v_july_v/article/details/7624837 (Accessed: 1 June 2012).
[2] Broder, A. (2002) ‘A taxonomy of web search’, ACM SIGIR Forum, 36(2), p. 3. doi: 10.1145/792550.792552.
[3] Burges, C.J.C., Laboratories, B. and Technologies, L. (1998) ‘A tutorial on support vector machines for pattern recognition.’, Data Mining and Knowledge Discovery, 2(2), pp. 121–167. doi: 10.1023/A1009715923555.
[4] Carreras, X. and M, L. (2001) ‘Boosting trees for Anti-Spam Email filtering’, .
[5] Chaitanya, K., Krishna, D.V.L.N. and Radha, P. (2015) A novel approach for classification of e-commerce data. Available at: http://dl.acm.org/citation.cfm?id=2835049&CFID=591715464&CFTOKEN=67347166 (Accessed: 17 March 2016).
[6] Derczynski, L., Wang, J., Gaizauskas, R. and Greenwood, M.A. (2008) ‘A data driven approach to query expansion in question answering’, Coling 2008: Proceedings of the 2nd workshop on Information Retrieval for Question Answering - IRQA ’08, . doi: 10.3115/1641451.1641456.
[7] Duan, H., Cao, Y., Lin, C.-Y. and Yu, Y. (2008) Searching questions by identifying question topic and question focus. Available at: http://anthology.aclweb.org/P/P08/P08-1019.pdf (Accessed: 10 August 2016).
[8] Elkan, C. (2008) Log-linear models and conditional random fields notes for a tutorial at CIKM’08. Available at: http://www.cs.columbia.edu/~smaskey/CS6998-0412/supportmaterial/cikmtutorial.pdf (Accessed: 10 August 2016).
[9] Garber, T., Goldenberg, J., Libai, B. and Muller, E. (2004) ‘From density to destiny: Using spatial dimension of sales data for early prediction of new product success’, 23(3), pp. 419–428. doi: 10.1287/mksc.1040.0051.
[10] Hu, M. and Liu, B. (2004a) ‘Mining and summarizing customer reviews’, Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery and data mining - KDD ’04, . doi: 10.1145/1014052.1014073.
[11] Hu, M. and Liu, B. (2004b) Mining Opinion Features in Customer Reviews. Available at: https://www.aaai.org/Papers/AAAI/2004/AAAI04-119.pdf (Accessed: 10 August 2016).
[12] Jain, J., Ghosh, R. and Dekhil, M. (2008) Multimodal capture of consumer intent in retail. Available at: http://dl.acm.org/citation.cfm?id=1358832&CFID=591715464&CFTOKEN=67347166 (Accessed: 13 April 2016).
[13] Jammalamadaka, R.C., Chittar, N. and Ghatare, S. (2009) Mining product intention rules from transaction logs of an ecommerce portal. Available at: http://dl.acm.org/citation.cfm?id=1620468&CFID=591715464&CFTOKEN=67347166 (Accessed: 13 April 2016).
[14] Katirai, H. (1999) Filtering junk e-mail: A performance comparison between genetic programming & Naïve Bayes. Available at: http://www.mit.edu/~hooman/papers/katirai99filtering.pdf (Accessed: 14 April 2016).
[15] khan, A., Baharudin, B. and khan, K. (2010) Sentence based sentiment classification from online customer reviews. Available at: http://dl.acm.org/citation.cfm?id=1943653&CFID=591715464&CFTOKEN=67347166 (Accessed: 13 April 2016).
[16] Kobayashi, M. and Ito, T. (2008) A Transactional Relationship Visualization System in Internet Auctions. Available at: http://delivery.acm.org/10.1145/1340000/1331665/30270248.pdf?ip=140.116.245.154&id=1331665&acc=ACTIVE%20SERVICE&key=AF37130DAFA4998B%2EEBD64A1DDB1C5FF0%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=653913164&CFTOKEN=62418101&__acm__=1470815964_42dba24b6633a83cd4ffe22f6837322d (Accessed: 2016).
[17] Koski, N. (2004) Impulse buying on the internet: Encouraging and discouraging factors. Available at: https://www.researchgate.net/publication/228688517_Impulse_buying_on_the_internet_Encouraging_and_discouraging_factors (Accessed: 10 August 2016).
[18] Linden, G., Smith, B. and York, J. (2003) Amazon.com recommendations. Available at: http://www.cin.ufpe.br/~idal/rs/Amazon-Recommendations.pdf (Accessed: 21 March 2016).
[19] Liu, F., Zhao, J., Lv, B., Xu, B. and Yu, H. (2005) Product named entity recognition based on hierarchical hidden Markov model *. Available at: http://www.aclweb.org/anthology/I05-3006 (Accessed: 10 August 2016).
[20] Ono, H. and Zavodny, M. (2009) ‘Gender and the Internet - Ono - 2009 - social science quarterly - Wiley Online library’, Social Science Quarterly, 84(1), pp. 111–121. doi: 10.1111/1540-6237.t01-1-8401007.
[21] Park, D.H., Kim, H.D., Zhai, C.X. and Guo, L. (2015) Retrieval of relevant opinion sentences for new products. Available at: http://dl.acm.org/citation.cfm?id=2767748 (Accessed: 2 February 2016).
[22] Piron, F. (1991) Defining impulse purchasing by Francis Piron. Available at: http://www.acrwebsite.org/search/view-conference-proceedings.aspx?Id=7206 (Accessed: 10 August 2016).
[23] Popescu, A.-M. and Etzioni, O. (2005) Extracting product features and opinions from reviews. Available at: http://turing.cs.washington.edu/papers/emnlp05_opine.pdf (Accessed: 10 August 2016).
[24] Sahami, M., Dumais, S., Heckerman, D., Horvitz, E. and Building, G. (no date) A B a yesian approach to filtering junk e-mail. Available at: http://research.microsoft.com/en-us/um/people/horvitz/spam.pdf (Accessed: 14 April 2016).
[25] Shen, D., Ruvini, J.-D., Somaiya, M. and Sundaresan, N. (2011) Item categorization in the e-commerce domain. Available at: http://dl.acm.org/citation.cfm?id=2063855 (Accessed: 22 March 2016).
[26] Thet, T.T., Na, J.-C. and Khoo, C.S.G. (2007) Filtering product reviews from web search results. Available at: http://dl.acm.org/citation.cfm?id=1284467&CFID=591715464&CFTOKEN=67347166 (Accessed: 13 April 2016).
[27] Wang, J.-C. and Chiu, C.-C. (2016) ‘Recommending trusted online auction sellers using social network analysis’, Expert Systems with Applications, 34(3), pp. 1666–1679. doi: 10.1016/j.eswa.2007.01.045.
[28] Wu, X. and Bolivar, A. (2009) Predicting the conversion probability for items on C2C ecommerce sites. Available at: http://dl.acm.org/citation.cfm?id=1646127&CFID=591715464&CFTOKEN=67347166 (Accessed: 23 March 2016).
[29] Wu, Y.-H. (2011) ‘Utilizing Online Auction Trading Information to Improve Matching Mechanism for Online Sellers’, http://etds.lib.ncku.edu.tw/etdservice/view_metadata?etdun=U0026-2408201123181600&class_search=yes&from=DEPT&fromid=D0026004003&query_field1=&query_word1=%E5%90%B3%E5%A5%95%E8%B3%A2: . .
[30] Yang, Y., Yan, Y., Qiu, M. and Sheng, F. (2007) Semantic analysis and helpfulness prediction of text for online product reviews. Available at: http://www.aclweb.org/anthology/P15-2007 (Accessed: 18 February 2016).
[31] You-ting, L. (2010) 問答機制影響線上拍賣結果之研究. Available at: http://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22097NCU05396021%22.&searchmode=basic (Accessed: 10 August 2016).