銷售預測為零售業重要之商務活動，目的在透過銷售預測消除庫存過剩與商品缺貨之問題，以提升營業績效。銷售預測之相關因素眾多，包括如景氣指標之參考因素，以及商品銷售影響因素如商品特徵與售價、天氣、行銷活動等。這些因素對預測準確度影響不一，篩選重要之銷售預測相關因素以提高預測準確度有其必要性。隨著網際網路的發達與社群媒體的普及，社群媒體對於消費者購買商品行為的影響與日俱增，如何從網路社群媒體資料中，萃取出有助銷售預測之因素與特徵以提升銷售預測準確率，也是當前銷售預測的課題。
本研究提出一考量社群媒體影響力與因素重要性之銷售預測方法，並開發實現技術，再驗證技術之正確性與方法之有效性。本方法包括:相關因素之資料收集與特徵分析、社群媒體影響力分析、重要因素分析、資料前處理、銷售預測等步驟。
本研究使用Y企業所提供的商品銷售數據進行驗證。首先建構情感分析模型，用以分析句子的極性與強度，經過10折的交叉驗證後，情感模型的Macro-F1達到76.96%。接著針對兩間商店的兩個商品分別進行實驗，結果顯示先進行重要影響因素分析者之均方根誤差分別降低了6%、12%、7%與20%，而平均絕對誤差分別降低了6%、6%、3%與23%，確認本研究所提基於重要影響因素之銷售預測方法與技術開發可行且有效。針對社群媒體影響力分析模型進行實作，發現使用社群媒體影響力有助於提高預測準確度。

Sales forecasting is an important business activity in the retail industry. The purpose of sales forecast is to eliminate the problem of over-stock and out-of-stock products in order to improve business performance. There are many factors related to sales forecasting, including reference factors such as economic indicators, as well as factors influencing product sales such as product characteristics and selling prices, weather, marketing activities, etc. These factors have varying influence on forecast accuracy, and it is necessary to select the important sales forecast-related factors to improve forecast accuracy. With the development of the Internet and the popularity of social media, the influence of social media on consumers' purchasing behavior is increasing day by day. How to extract the factors and characteristics that can help sales forecasting from online social media data to improve the accuracy of sales forecast is also a current issue in sales forecasting.

This research proposes a sales forecast method that takes into account the influence of social media and the importance of factors, and develops a realistic technique to test the validity of the technique and the method.

This research was conducted using the sales data provided by company Y. First of all, the sentiment model was constructed to analyze the polarity and intensity of the sentences, and the Macro-F1 of the sentiment model reached 76.96% after 10-fold cross-validation. Then, the experiment was conducted for two products in two stores. The results of the experiment proved that the RMSE was reduced by 6%, 12%, 7% and 20%, and the MAE was reduced by 6%, 6%, 3% and 23%, respectively, so that the sales forecasting method and technology development based on the significant influence factors is feasible and effective. Conducting a hands-on social media impact analysis model.It is found that social media influence can help to improve the accuracy of forecast, so the social media influence analysis model proposed in this research is feasible and effective.

Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan), 993-1022.
Bermingham, M. L., Pong-Wong, R., Spiliopoulou, A., Hayward, C., Rudan, I., Campbell, H., ... & Haley, C. S. (2015). Application of high-dimensional feature selection: evaluation for genomic prediction in man. Scientific reports, 5(1), 1-12.
Bohanec, M., Kljajić Borštnar, M., & Robnik-Šikonja, M. (2015, September). Feature subset selection for B2B sales forecasting. In Proceedings of 13th International Symposium on Operational Research, SOR (Vol. 15, pp. 285-290).
Behera, G., & Nain, N. (2019, September). A comparative study of big mart sales prediction. In International Conference on Computer Vision and Image Processing (pp. 421-432). Springer, Singapore.
Berry, L. R., Helman, P., & West, M. (2020). Probabilistic forecasting of heterogeneous consumer transaction–sales time series. International Journal of Forecasting, 36(2), 552-569.
Birjali, M., Kasri, M., & Beni-Hssane, A. (2021). A comprehensive survey on sentiment analysis: Approaches, challenges and trends. Knowledge-Based Systems, 226, 107134.
Bouhadana, G., Chocron, Y., Zammit, D., & Gilardino, M. S. (2022). Usage trends, perceptions and ethical views regarding social media: A survey of Canadian plastic surgeons. Journal of plastic, reconstructive & aesthetic surgery : JPRAS, 75(3), 1261–1282.
Balakrishnan, V., Ng, K. S., & Arabnia, H. R. (2022). Unravelling social media racial discriminations through a semi-supervised approach. Telematics and Informatics, 67, 101752.
Contreras, J., Espinola, R., Nogales, F. J., & Conejo, A. J. (2003). ARIMA models to predict next-day electricity prices. IEEE transactions on power systems, 18(3), 1014-1020.
Chu, C. W., & Zhang, G. P. (2003). A comparative study of linear and nonlinear models for aggregate retail sales forecasting. International Journal of production economics, 86(3), 217-231.
Chen, Y. (2015). Convolutional neural network for sentence classification (Master's thesis, University of Waterloo).
Chun-Yao, H., & Ping-Yu, L. (2016). Electronic WOM and online review–a literature Review. Tai Da Guan Li Lun Cong, 26(3), 215.
Chen, T., & Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
Chen, T., Yin, H., Chen, H., Wu, L., Wang, H., Zhou, X., & Li, X. (2018, November). Tada: trend alignment with dual-attention multi-task recurrent neural networks for sales prediction. In 2018 IEEE international conference on data mining (ICDM) (pp. 49-58). IEEE.
Chen, J., Song, L., Wainwright, M., & Jordan, M. (2018, July). Learning to explain: An information-theoretic perspective on model interpretation. In International Conference on Machine Learning (pp. 883-892). PMLR.
Chen, F., & Huang, Y. (2019). Knowledge-enhanced neural networks for sentiment analysis of Chinese reviews. Neurocomputing, 368, 51-58.
Chonko, L. B. (2021). Advanced Introduction to Sustainable Competitive Advantage in Sales. Edward Elgar Publishing.
Duch, W. (2006). Filter methods. In Feature Extraction (pp. 89-117). Springer, Berlin, Heidelberg.
Dreyer, S. (2013).Evolutionary feature selection, in: Norwegian University of Science and Technology, Department of Computer and Information Science, Institutt for datateknikk og informasjonsvitenskap, p. 76.
De Medeiros, J. F., Ribeiro, J. L. D., & Cortimiglia, M. N. (2016). Influence of perceived value on purchasing decisions of green products in Brazil. Journal of Cleaner Production, 110, 158-169
Das, A. K., Pati, S. K., & Ghosh, A. (2020). Relevant feature selection and ensemble classifier design using bi-objective genetic algorithm. Knowledge and Information Systems, 62(2), 423-455.
Elmasdotter, A., & Nyströmer, C. (2018). A comparative study between LSTM and ARIMA for sales forecasting in retail.
Filieri, R., & McLeay, F. (2014). E-WOM and Accommodation: An Analysis of the Factors That Influence Travelers’ Adoption of Information from Online Reviews. Journal of Travel Research, 53(1), 44–57.
Goldberg, Y., & Levy, O. (2014). word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method. arXiv preprint arXiv:1402.3722.
Gao, S., Tang, O., Wang, H., & Yin, P. (2018). Identifying competitors through comparative relation mining of online reviews in the restaurant industry. International Journal of Hospitality Management, 71, 19-32.
Güven, İ., Şimşir, F. (2020)Demand forecasting with color parameter in retail apparel industry using artificial neural networks (ANN) and support vector machines (SVM) methods. Computers & Industrial Engineering, Volume 147.
Hochreiter, S.,&Schmidhuber, J. (1997). Long short-term memory. Neural computation, 9(8), 1735-1780.
Hayes, B. D., Kobner, S., Trueger, N. S., Yiu, S., & Lin, M. (2015). Social media in the emergency medicine residency curriculum: social media responses to the residents' perspective article. Annals of emergency medicine, 65(5), 573–583.
Hussain, A., & Cambria, E. (2018). Semi-supervised learning for big social data analysis. Neurocomputing, 275, 1662-1673.
Jurek, A., Mulvenna, M. D., & Bi, Y. (2015). Improved lexicon-based sentiment analysis for social media analytics. Security Informatics, 4(1), 1-13.
Kaneko, Y., & Yada, K. (2016, December). A deep learning approach for the prediction of retail store sales. In 2016 IEEE 16th International conference on data mining workshops (ICDMW) (pp. 531-537). IEEE.
Karimi, S., & Wang, F. (2017). Online review helpfulness: Impact of reviewer profile image. Decis. Support Syst., 96, 39-48.
Kawai, M., Sato, H., & Shiohama, T. (2022). Topic model-based recommender systems and their applications to cold-start problems. Expert Systems with Applications, 117129.
Lee, S. A., & Jeong, M. (2012). Effects of e‐servicescape on consumers' flow experiences. Journal of Hospitality and Tourism Technology.
Lee, E. (2013). Impacts of social media on consumer behavior: decision making process.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.
Li, Y., Pan, Q., Yang, T., Wang, S., Tang, J., & Cambria, E. (2017). Learning word representations for sentiment analysis. Cognitive Computation, 9(6), 843-851.
Lin, Z., Madotto, A., Winata, G. I., Liu, Z., Xu, Y., Gao, C., & Fung, P. (2019, August). Learning to learn sales prediction with social media sentiment. In Proceedings of the First Workshop on Financial Technology and Natural Language Processing (pp. 47-53).
Li, F., Lai, L., & Cui, S. (2021). On the adversarial robustness of LASSO based feature selection. IEEE Transactions on Signal Processing, 69, 5555-5567.
Li, Q., Zhu, Y., Shangguan, W., Wang, X., Li, L., & Yu, F. (2022). An attention-aware LSTM model for soil moisture and soil temperature prediction. Geoderma, 409, 115651.
Loureiro, A.L., Miguéis, V.L., & Silva, L.F. (2018). Exploring the use of deep neural networks for sales forecasting in fashion retail. Decis. Support Syst., 114, 81-93.
Luo, J., Zhang, Z., Fu, Y., & Rao, F. (2021). Time series prediction of COVID-19 transmission in America using LSTM and XGBoost algorithms. Results in Physics, 27, 104462.
Ludwig, N., Feuerriegel, S., & Neumann, D. (2015). Putting Big Data analytics to work: Feature selection for forecasting electricity prices using the LASSO and random forests. Journal of Decision Systems, 24(1), 19-36.
Ma, W., & Chen, K. (2004). Design of CKIP Chinese Word Segmentation System. J. Chin. Lang. Comput., 14.
Marcano-Cedeño, A., Quintanilla-Domínguez, J., Cortina-Januchs, M.G., & Andina, D. (2010). Feature selection using Sequential Forward Selection and classification applying Artificial Metaplasticity Neural Network. IECON 2010 - 36th Annual Conference on IEEE Industrial Electronics Society, 2845-2850.
Maruyama, S., & Moriya, S. (2021).Newton's Law of Cooling: Follow up and exploration. International Journal of Heat and Mass Transfer, 164, 120544.
Miswan, N. H., Chan, C. S., & Ng, C. G. (2021). Hospital readmission prediction based on improved feature selection using grey relational analysis and LASSO. Grey Systems: Theory and Application.
Mou, S., Robb, D. J., & DeHoratius, N. (2018). Retail store operations: Literature review and research directions. European Journal of Operational Research, 265(2), 399-422.
Nash, J. (2018). Exploring how social media platforms influence fashion consumer decisions in the UK retail sector. Journal of Fashion Marketing and Management: An International Journal.
Nithin, S. S., Rajasekar, T., Jayanthy, S., Karthik, K., & Rithick, R. R. (2022, March). Retail Demand Forecasting using CNN-LSTM Model. In 2022 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 1751-1756). IEEE.
Oneto, L., Bisio, F., Cambria, E., & Anguita, D. (2016). Statistical learning theory and ELM for big social data analysis. ieee CompUTATionAl inTelliGenCe mAGAzine, 11(3), 45-55.
Ord, K., Fildes, R., & Kourentes, N. (2017). Principles of Business Forecasting, Wessex, 2nd.
Pantano, E., & Timmermans, H. (2014). What is smart for retailing?. Procedia Environmental Sciences, 22, 101-107.
Pennington, J., Socher, R., & Manning, C. D. (2014, October). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532-1543).
Park, J., & Kwon, H. (2021). Cyberattack detection model using community detection and text analysis on social media. ICT Express.
Peng, S., Cao, L., Zhou, Y., Ouyang, Z., Yang, A., Li, X., ... & Yu, S. (2021). A survey on deep learning for textual emotion analysis in social networks. Digital Communications and Networks.
Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. science, 290(5500), 2323-2326.
Rong, W., Nie, Y., Ouyang, Y., Peng, B., & Xiong, Z. (2014). Auto-encoder based bagging architecture for sentiment analysis. Journal of Visual Languages & Computing, 25(6), 840-849.
Rajalakshmi, S., Asha, S., & Pazhaniraja, N. (2017). A comprehensive survey on sentiment analysis. In 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN) (pp. 1-5). IEEE.
Rese, A., Ganster, L., & Baier, D. (2020). Chatbots in retailers’ customer communication: How to measure their acceptance?. Journal of Retailing and Consumer Services, 56, 102176.
Sun, X., & Ni, Y. (2006). Recurrent neural network with kernel feature extraction for stock prices forecasting. In 2006 International Conference on Computational Intelligence and Security (Vol. 1, pp. 903-907). IEEE.
Sun, J. (2012). Jieba chinese word segmentation tool.
Sharfuddin, A. A., Tihami, M. N., & Islam, M. S. (2018, September). A deep recurrent neural network with bilstm model for sentiment classification. In 2018 International conference on Bangla speech and language processing (ICBSLP) (pp. 1-4). IEEE.
Sun, Q., Niu, J., Yao, Z., & Yan, H. (2019). Exploring eWOM in online customer reviews: Sentiment analysis at a fine-grained level. Eng. Appl. Artif. Intell., 81, 68-78.
Sharma, P., & Sharma, A. K. (2020). Experimental investigation of automated system for twitter sentiment analysis to predict the public emotions using machine learning algorithms. Materials Today: Proceedings.
Tollo, G. D., & Lyra, M. (2010). Elman nets for credit risk assessment. In Decision Theory and Choices: a Complexity Approach (pp. 147-167). Springer, Milano.
Taboada, M., Brooke, J., Tofiloski, M., Voll, K., & Stede, M. (2011). Lexicon-based methods for sentiment analysis. Computational linguistics, 37(2), 267-307.
Tao, H., Robert F., & Didier, S. (2014) The value of competitive information in forecasting FMCG retail product sales and the variable selection problem. European Journal of Operational Research, Elsevier, vol. 237(2), pages 738-748.
Vithayathil, J., Dadgar, M., & Osiri, J. K. (2020). Social media use and consumer shopping preferences. International Journal of Information Management, 54, 102117.
Triayudi, A., Sumiati, S.,Nurhadiyan, T., & Rosalina, V. (2020). Data mining implementation to predict sales using time series method. Proceeding of the Electrical Engineering Computer Science and Informatics, 7(2), 1-6.
Wang, W. J., Liao, Y. F., & Chen, S. H. (2002). RNN-based prosodic modeling for mandarin speech and its application to speech-to-text conversion. Speech Communication, 36(3-4), 247-265.
Wei, J., Liao, J., Yang, Z., Wang, S., & Zhao, Q. (2020). BiLSTM with multi-polarity orthogonal attention for implicit sentiment analysis. Neurocomputing, 383, 165-173.
Wang, C. H. (2022). Considering economic indicators and dynamic channel interactions to conduct sales forecasting for retail sectors. Computers and Industrial Engineering, 165, [107965].
Xu, G., Yu, Z., Yao, H., Li, F., Meng, Y., & Wu, X. (2019). Chinese text sentiment analysis based on extended sentiment dictionary. IEEE Access, 7, 43749-43762.
Yeshin, T. (2006). Advertising. Cengage Learning EMEA.
Yong, Z.,Dun-wei, G., & Wan-Qiu Z.(2016). Feature selection of unreliable data using an improved multi-objective PSO algorithm Neurocomputing, 171, pp. 1281-1290
Yi-Siou, Y. (2019).The Research of the Correlation between Social Network and Vote of Internet Public Opinion from Social Media -A case study of the Mayor of Kaohsiung HAN GUO YU
Zhu, Y., & Chen, H. (2015). Social media and human need satisfaction: Implications for social media marketing. Business Horizons, 58, 335-345.
林佩君,(2020).深度學習應用於部落格文章分類，臺灣大學工程科學及海洋工程學研究所，學位論文。
胡博文 & 李軍，(2021).基于多層LSTM的電商商品销售预测。
孫建旺,呂學強 & 張雷瀚， (2014). 基於詞典與機器學習的中文微博情感分析研究. 計算機應用與軟件, 31(7), 177-181.
陳宜棻,(2010).從展望理論觀點探討網路口碑對消費者購買意願之影響. 電子商務學報, 12(3), 527-546.
陳建安,(2021).以影響力為基之市場區隔趨勢預測方法與技術研發，國立成功大學製造資訊與系統研究所，碩士論文。。
劉夢曉,(2017).負面在線評論和商家反饋對消費者購買意願的影響研究. 電子商務學報, 19(1), 83-116.