Toplantı tutanaklarının analizi ile bir karar destek sistemi

Günümüzde veri madenciliği firmalar açısından çok önemli hale gelmiştir. Firmalar sektörde rekabet avantajı sağlayabilmek için veri madenciliği tekniklerini kullanarak büyük veriden işlerine yarayacak, daha önceden keşfedilmemiş, kullanılabilir örüntüler elde eder. Gelişen haberleşme teknolojileri sonucu firmalarda biriken veri yığınları, firmalar için hayati önem taşıyan bilgileri içinde barındırır. Karar vericiler, klasik tekniklerle bu verilerden çıkarımlarda bulunurken, önemli bilgileri gözden kaçırırlar. Veriyi doğru yönetemeyen firmalar ise işlerine yaramayan veri yığınlarında kaybolur. Bir işletmeye ait sayısal platformdaki bu verilerin %80’i metin formundadır. Ancak yapısal olmayan verileri de içeren büyük veri klasik istatistiksel tekniklerle analiz edilen veriler kadar kolay işlenemez. Doğal dil işleme tekniklerinden faydalanılması gerekmektedir. Böylece, soyut ve yığın yapısal olmayan bilgiler, sayısal somut ifadelere dönüştürülebilmektedir. Bu araştırma, Kayseri’de bir imalat fabrikasında yapılan üst düzey toplantıların metin formatındaki tutanaklarını analiz ederek bilgi çıkarımı gerçekleştirmektedir. Yöneticilerin verdiği stratejik kararlarda önemli toplantı sonuçları çok etkilidir. Araştırmanın en genel amacı toplantıların kalitesini artırmaktır. Araştırmada, toplantı tutanaklarından kelime çıkarımı yapılarak, toplantılara ait genel konu başlıkları metin madenciliği ile elde edilecektir. Yöneticiler çeşitli madenleme teknikleriyle gruplanmış konu başlıklarına göre değerlendirme yaparak sonraki toplantıların kalitesini artırarak zaman kazanabilir.

Anahtar Kelimeler:

Metin madenciliği, Doğal dil işleme, Yönetim, Üretim Toplantı Raporları

A decision support system by analysis of the meeting reports

Recently, data mining has become crucial for firms. Using data mining, Firms, in order to have comparative advantage in industry / sector / market, obtain patterns that they can utilize and that have not been discovered before. The data accumulated as a result of the advanced communication channels within firms contain crucial information. Decision makers’ undersees important information while they use classical techniques for data analysis. Firms that cannot manage data accurately get lost in piles of data that would not be useful for them. 80% of the data in the quantitative platform belonging to a firm is in text format. However, large data containing non-structural data cannot be analyzed as easily as the data analyzed by using classical statistical techniques. Natural language analysis techniques should be used. In this way, abstract and non-structural data can be converted into concrete and quantitative statements. In this analysis, information is inferred by the analysis of transcripts—in text format—of meetings among senior managers at a manufacturing company in Kayseri. Outcomes of the important meetings are very crucial in the decisions the directors take. The main goal of the study is to increase the efficiency of the meetings. In this research, the general themes of the meetings are found out by word inference from the meeting transcripts. Directors can have better time-management by increasing the quality of the future meetings by conducting evaluations according to the topics categorized by the data mining techniques.

Keywords:

Text Mining, Natural language processing, Management, Manufacturing meeting reports,

PDF

___

[1] Thorleuchter D., Den Poel D. V., Prinzie A., (2010). “Mining ideas from textual information,” Expert Systems with Applications, vol. 37, pp. 7182–7188. [2] Rose, S., Engel, D., Cramer, N., Cowley, W., (2010), “Automatic keyword extraction from individual documents”, in: M.W. BERRY and J. KOGAN (Ed.), TM: Applications and Theory, Wiley, p.3-19. [3] Kumar, S., Nassehi, A., Newman S.T., Tiwari, M. K., (2007), “Process control in CNC manufacturing for discrete components: A STEP-NC compliant framework”, Robotics and Computer Integrated Manufacturing, 23, pp.667-676. [4] Li, D.C., Yeh C.W., (2008), “A non-parametric learning algorithm for small manufacturing data sets”, Expert Systems with Applications, 34, pp.391– 398. [5] Çi̇fli̇kli̇, C., Kahya-Özyi̇rmi̇dokuz, E., (2010), “Implementing A Data Mining Solution For Enhancing Carpet Manufacturing Productivity”, Knowledge Based Systems, 23 (8) Pp.783-788. [6] Gebus, S., Leiviska, K. (2009), “Knowledge acquisition for decision support systems on an electronic assembly line”, Expert Systems with Applications, 36 (1), pp. 93-101. [7] Kusiak, A., Smith M., (2007), “Data mining in design of products and production systems”, Annual Reviews in Control, 31, pp.147–156. [8] Kang, P., Lee H., Cho S., Kim, D., Park, J., Park, J. K., Doh, S., (2009), “A virtual metrology system for semiconductor manufacturing”, Expert Systems with Applications, 36, pp.12554–12561. [9] Durán, O., Rodriguez, N., Consalter, L.A., (2010), “Collaborative particle swarm optimization with a data mining technique for manufacturing cell design”, Expert Systems with Applications, 37, pp.1563–1567. [10] Liao, S. H., Chu, P. H., Hsiao, P. Y., (2012), “Data mining techniques and applications – A decade review from 2000 to 2011”, Expert Systems with Applications, 39, pp.11303–11311. [11] Harding, J.A., Shahbaz, M., Srinivas, Kusiak, A., (2006), “Data mining in manufacturing: A review”, Journal of Manufacturing Science and Engineering, Manufacturing Engineering Division of Asme 128, pp. 969- 976. [12] Wang, K. (2007), “Applying data mining to manufacturing: the nature and implications”, Journal of Intelligent Manufacturing, 18 pp.487–495. [13] Çi̇fli̇kli̇, C., Kahya-Özyi̇rmi̇dokuz, E., (2012), "Enhancing Product Quality Of a Process", Industrial Management and Data Systems, 112, pp.1181-1200. [14] Ittoo, A., Bouma G., (2013), “Term extraction from sparse, ungrammatical domain-specific documents”, Expert Systems with Applications, 40, pp.2530–2540. [15] Thorleuchter, D., Van Den Poel, D., (2014), “Semantic compared cross impact analysis”, Expert Systems with Applications 41, pp. 3477– 3483. [16] Kahya-Özyi̇Rmi̇Dokuz, E., (2014), “Analyzing Social Network Unstructured Data”, Information Development, doi: 10.1177/0266666914528523. [17] Kahya Özyi̇rmi̇dokuz, E., Özyi̇rmi̇dokuz M. H., (2014) “Analyzing Customer Complaints : A Web Text Mining Application", in International Conference on Education and Social Sciences (INTCESS14), Ferit USLU (Ed.), İstanbul, 3-5 February 2014, pp.734-743. [18] Liu, Y., Lu, W. F., Loh, H. T., (2006), “A Framework of information and knowledge management for product design and development: A text mining approach”, Information Control Problems in Manufacturing IFAC 12th, in INCOM 2006, Information control problems in manufacturing, pp. 635-640. [19] Negahban, A., Smith, J.S., (2014), “Simulation for manufacturing system design and operation: Literature review and analysis”, Journal of Manufacturing Systems, 33 (2), pp.241–261. [20] Chang C.W., Lin C.T., Wang L.Q., (2009). “Mining the text information to optimizing the customer relationship management,” Expert Systems with Applications, vol. 36, pp. 1433–1443.
[21] Gamon M., (2004). “Sentiment classification on customer feedback data: Noisy data, large feature vectors, and the role of linguistic analysis,” in Proc. the 20th international conference on Computational Linguistics, pp. 841-847, PA, USA: Association for Computational Linguistics Stroudsburg. [22] Gamon M., Aue A., Corston-Oliver S., Ringger E., (2005). “Pulse: Mining customer opinions from free text,” LNCS, pp. 121-132, Heidelberg, Berlin: Springer-Verlag. [23] Ittoo A. R., Zhang Y. R., Jiao J., (2006). “A TM based recommendation system for customer decision making in online product customization,” in Proc. International Conference on Management of innovation and technology, vol. 1, pp. 473-477, Singapore, China: IEEE. [24] Coussement K., Den Poel D. V., (2008). “Improving customer complaint management by automatic email classification using linguistic style features as predictors,” Decision Support Systems, vol. 44, pp. 870–882. [25] Weng S.S., Liu C.K., (2004). “Using text classification and multiple concepts to answer e-mails,” Expert Systems with Applications, vol. 26, pp. 529–543. [26] Özyurt Ö., Köse C., (2010). “Chatmining: Automatically determination of chat conversations’ topic in Turkish text based chat mediums,” Expert Systems with Applications, vol. 37, pp. 8705–8710. [27] Tsai S., Kwee A. T., (2011). “Database optimization for novelty mining of business blogs,” Expert Systems with Applications, vol. 38, pp. 11040–11047. [28] Gopal R. D., Marsden J. R., Vanthienen J., (2011). “Information mining - Reflections on recent advancements and the road ahead in data, text, and media mining,” Decision Support Systems, vol. 51, pp. 727–731. [29] Sunikka A., Bragge J., (2012). “Applying text-mining to personalization and customization research literature – Who, what and where?” Expert Systems with Applications, vol. 39, pp. 10049–10058. [30] Onishi H., Manchanda P., (2012). “Marketing activity, blogging and sales,” Intern. J. of Research in Marketing, vol. 29, pp. 221–234. [31] Armentano M. G., Godoy D., Amandi A. A., (2013). “Followee recommendation based on text analysis of micro-blogging activity,” Information Systems, vol. 38, pp. 1116-1127. [32] Thorleuchter D., DenPoel D.V., (2012). “Predictinge-commercecompany success by mining the text of its publicly-accessible website,” Expert Systems with Applications, vol. 39, pp. 13026–13034. [33] Thorleuchter D., Den Poel D. V., Prinzie A., (2012). “Analyzing existing customers’ websites to improve the customer acquisition process as well as the profitability prediction in B-to-B marketing,” Expert Systems with Applications, vol. 39, pp. 2597–2605. [34] Ur-Rahman N., Harding J. A., (2012). “Textual DM for industrial knowledge management and text classification: A business oriented approach,” Expert Systems with Applications, vol. 39, pp. 4729–4739. [35] Hao Z.G., (2012). “A new text clustering method based on KSEP,” Journal of Software, vol. 7, no. 6, pp. 1421-1425. [36] He W., Zha S., Li L., (2013). “Social media competitive analysis and TM: A case study in the pizza industry,” International Journal of Information Management, vol.33, no.3, pp. 464–472. [37] Kahya Özyirmidokuz E., (2014). “Analyzing unstructured facebook social network data through web TM: A study of online shopping firms in Turkey,” Information Development, pp. 1–12, 2014. [38] Ordenes F. V., Theodoulidis B., Burton J., Gruber T., Zaki M., (2014). “Analyzing customer experience feedback using TM: A linguistics-based approach,” Journal of Service Research, pp. 1-18. [39] Stray, V., Dag I.K., Sjøberg, T. D., (2016). “The daily stand-up meeting: A grounded theory study”, The Journal of Systems and Software 114, 101–124. [40] Kim, S. H., Park, S., Sun, M. R., Lee, J. H., (2016). “A Study of Smart Beacon-based Meeting, Incentive Trip, Convention, Exhibition and Event (MICE) Services Using Big Data”, Procedia Computer Science 91, 761 – 768. [41] Hussain, S. F., Suryani, A., (2015). “On retrieving intelligently plagiarized documents using semantic similarity”, Engineering Applications of Artificial Intelligence 45, 246–258. [42] Zhang, H., Chow, T.W.S., (2012). “A multi-level matching method with hybrid similarity for document retrieval”, Expert Systems with Applications 39, 2710–2719. [43] Hotho, A., Nurnberger, A., Paaß, G., (2005). “A Brief Survey of Text Mining. LDV Forum – GLDV”, Journal for Computational Linguistics and Language Technology 20(1), 19-62. [44] Tuffery, S. (2011), DM and Statistics for Decision Making. Wiley [45] Larose, D. T., (2005), Discovering Knowledge in Data: An Introduction to Data Mining, USA: Wiley. [46] Sumathi, S., Sivanandam, S.N. (2006). Introduction to DM and its Applications, Verlag Berlin Heidelberg: Springer. [47] Hoffmann and Klinkenberg, 2014 RapidMiner: Data Mining Use Cases and Business Analytics Applications, Markus Hofmann, Ralf Klinkenberg, CRC Press, Taylor and Francis [48] Ingersoll, G.S.; Morton, T.S.; Farris, A.L. (2013) Taming Text: How to Find, Organize, and Manipulate it, Liddy, L. (Ed.). NY: Manning Publications and Co [49] Ghosh, J., Strehl, A., (2006). “Similarity-Based Text Clustering: A Comparative Study, in: Grouping Multidimensional Data: Recent Advances in Clustering”, Jacob Kogan, Charles Nicholas, Marc Teboulle (Eds.), Springer-Verlag Berlin Heidelberg, pp. 73-98.