現今是個網路發達的時代，網路資源越來越豐富，消費者受網路口碑的影響也持續增加，使用社群論壇來分享使用經驗及產品的評論，因此評論篇幅與日俱增，所以消費者要購買產品前，就需要在數篇評論中歸納、分類來了解產品的優劣。除了評論篇數多之外，回覆內容會因為使用者的用字遣詞或個性不同而不同，有些簡明扼要但有些長篇大論，這種資訊過載要如何讓消費者從中獲得重要的資訊這是本研究的想探討議題。
本研究首先收集社群論壇的主題及回覆，並利用實體辨識的方法將評論的對象擷取出來，使用N-Gram的方法將評論與產品名稱列表進行實體的辨識，接著利用語句中詞性的排列擷取出面向，以銜接後續情緒的分析。最後，利用雷達圖將不同的面向資訊呈現給使用者，讓使用者透過視覺的呈現，能在購物前快速了解產品的相關資訊。本研究會以智慧型手機評論為例，並以目前網路盛行之社群論壇評論Mobile01作為資料來源，針對使用者在評論中使用的情緒用詞進行極性分類，再進行視覺呈現以協助消費者選擇適合的手機。

Nowadays, the Internet is highly developed. The information and resources from the Internet are abundant and rich, and these sources are continued to grow every day. Consumers’ buying behaviors are influenced by word of mouth on the network. People share their use of product experience on online community forums, and this information increases greatly daily. Before purchasing a product, consumers need to summarize and categorize several reviews to analyze the pros and cons of the product. This research aims to discuss how consumers can obtain important information that they want in this age of information overload. First of all, this research collects topics and responses from the community forums online and applies the method of Named Entity Recognition to select the target of the object, and then the lists of the comments and product names are retrieved to be identified by using the N-Gram method. Also, to perform the method “sentiment analysis,” the aspects are extracted according to the arrangement of words in the sentence. Finally, different aspects of the information are presented to the users on the radar chart, to quickly understand the product information through a visual presentation before purchasing. This study will take smartphone reviews as an example and use the mobile phone reviews from Mobile01, which is a currently popular Internet social forum, as a data source. The emotional words used in the reviews will be classified the polarity and then put into a visual presentation to help consumers choose a suitable mobile phone.

英文文獻
Abu Al-Haija, Q., & Zein-Sabatto, S. (2020). An Efficient Deep-Learning-Based Detection and Classification System for Cyber-Attacks in IoT Communication Networks. Electronics, 9(12), 2152.
Aksakalli, V., & Malekipirbazari, M. (2016). Feature selection via binary simultaneous perturbation stochastic approximation. Pattern Recognition Letters, 75, 41-47.
Chen, W.-F., Ku, L.-W., & Lee, Y.-H. (2015). Mining supportive and unsupportive evidence from facebook using anti-reconstruction of the nuclear power plant as an example. Paper presented at the 2015 AAAI Spring Symposium Series.
El-Hasnony, I. M., Barakat, S. I., Elhoseny, M., & Mostafa, R. R. (2020). Improved feature selection model for big data analytics. IEEE Access, 8, 66989-67004.
Gokalp, O., Tasci, E., & Ugur, A. (2020). A novel wrapper feature selection algorithm based on iterated greedy metaheuristic for sentiment classification. Expert Systems with Applications, 146, 113176.
Huang, Z., Xu, W., & Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991.
Kolluru, B., Hawizy, L., Murray-Rust, P., Tsujii, J., & Ananiadou, S. (2011). Using workflows to explore and optimise named entity recognition for chemistry. PloS one, 6(5), e20181.
Ku, L. W., Ho, H. W., & Chen, H. H. (2009). Opinion mining and relationship discovery using CopeOpi opinion analysis system. Journal of the American Society for Information Science and Technology, 60(7), 1486-1503.
Lafferty, J., McCallum, A., & Pereira, F. C. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data.
Lee, A. J., Yang, F.-C., Chen, C.-H., Wang, C.-S., & Sun, C.-Y. (2016). Mining perceptual maps from consumer reviews. Decision Support Systems, 82, 12-25.
Lee, C. (2017). LSTM-CRF models for named entity recognition. IEICE transactions on information and systems, 100(4), 882-887.
Liu, F., Baldwin, T., & Cohn, T. (2017). Capturing long-range contextual dependencies with memory-enhanced conditional random fields. arXiv preprint arXiv:1709.03637.
Majumder, N., Bhardwaj, R., Poria, S., Zadeh, A., Gelbukh, A., Hussain, A., & Morency, L.-P. (2020). Improving Aspect-Level Sentiment Analysis with Aspect Extraction. arXiv preprint arXiv:2005.06607.
Malekipirbazari, M., Aksakalli, V., Shafqat, W., & Eberhard, A. (2021). Performance comparison of feature selection and extraction methods with random instance selection. Expert Systems with Applications, 179, 115072.
Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams engineering journal, 5(4), 1093-1113.
Mudambi, S. M., & Schuff, D. (2010). What makes a helpful online review? A study of customer reviews on Amazon. com. MIS Quarterly, 34(1), 185-200.
Peters, M. E., Ammar, W., Bhagavatula, C., & Power, R. (2017). Semi-supervised sequence tagging with bidirectional language models. arXiv preprint arXiv:1705.00108.
Rees, D., & Laramee, R. S. (2019). A survey of information visualization books. Paper presented at the Computer Graphics Forum.
Ren, Z., Zeng, G., Chen, L., Zhang, Q., Zhang, C., & Pan, D. (2020). A Lexicon-Enhanced Attention Network for Aspect-Level Sentiment Analysis. IEEE Access, 8, 93464-93471.
Rodriguez, J. D., Perez, A., & Lozano, J. A. (2009). Sensitivity analysis of k-fold cross validation in prediction error estimation. IEEE transactions on pattern analysis and machine intelligence, 32(3), 569-575.
Sarkar, K., & Shaw, S. K. (2017). A memory-based learning approach for named entity recognition in Hindi. Journal of Intelligent Systems, 26(2), 301-321.
Zhang, H., Boons, F., & Batista-Navarro, R. (2019). Whose story is it anyway? Automatic extraction of accounts from news articles. Information Processing & Management, 56(5), 1837-1848.
Zhu, F., & Zhang, X. (2010). Impact of online consumer reviews on sales: The moderating role of product and consumer characteristics. Journal of marketing, 74(2), 133-148.

網路資料
1. Alexa.2020.Alexa Top Sites in Taiwan Retrieved August 2nd,2020,from https://www.alexa.com/topsites/countries/TW
2. Mobile01.2020.Mobile 01 論壇 Retrieved August 2nd,2020,from https://www.mobile01.com/
3. Visual Content Marketing: Why Content with Visuals Get 94% More Views (afteroffers.com)
4. Cross-validation (statistics) - Wikipedia
5. https://www.analyticsvidhya.com/blog/2016/12/introduction-to-feature-selection-methods-with-an-example-or-how-to-select-the-right-variables/