Limitations of the Study

This is a limited study where we have only investigated the CEBs across few companies. This means that the results are not generalizable beyond these companies.

We also have no knowledge of the content through which the comment was made in terms of the posts

and other comments and comment-replies. So we cannot say anything about what drives the different

behaviours. We are also not able to say anything about why the customers express their CEBs and what

specific consequences these have.

79 of 80

9. Conclusion and Answers to Research Questions

Throughout this thesis we have investigated the customer engagement behaviours in the comments on company Facebook profiles. Based on academic literature on customer engagement behaviours and through inspecting the comments, we propose that there are 8 different customer engagement

behaviours expressed in the comments. These are; Feedback, Opinion, Customer Service, Reply, Social Interaction, Trolling, Controversy and Other. The Feedback-comments are those that provide concrete and actionable information and the Opinion-comments are subjective opinions of the company or the products and services. Customer Service are comments seeking assistance from the company, Reply are comments directly replying to a company post and Social Interactions are mainly comments where the customer tags another user. Trolling-comments are those that are malicious and anti-social and Controversy-comments contain commentary about some controversy surrounding the company.

These CEB were investigated in the comments of 10 different companies. This was done using 5 different supervised machine learning algorithms; Naïve Bayes, linear support vector classifier, logistic regression, passive aggressive classifier and a support vector machine fitted with stochastic gradient descent. Transforming the text to a numeric data structure using several text pre-processing steps, bag-of-words approach and td-idf weights, these algorithms were trained using a manually labelled subset of the data. The classifiers were subsequently used to classify all the comments across the 10 different companies’ datasets according to their class membership to the customer engagement behaviours, sentiment and intensity. Though we found some performance issues with these classifiers this was eased by the influential features used by the classifiers, which showed that they used words that were very indicative of the categories.

Based on this classification we found that the majority of the CEBs expressed are Social Interactions, Opinion and for those companies that use this strategy; Reply. Both airlines, Ryanair and British Airways get a lot of Reply-comments, and so do Lloyds Bank. We also find that the low cost airline Ryanair gets a lot more negative Opinion comments compared to British Airways that cater to a different price point. All the companies get very few comments that are Trolling and Controversy.

However, we are able to see how companies, such as Volkswagen and HSBC UK, that were embroiled

in scandals, experience a short surge in Controversy comments. On the Banks’ profiles there are more

80 of 80 Customer Service and Feedback comments and less Opinion and Social Interaction-comments

indicating that their customers use Facebook in a more practical way to reach the company. For most of the companies the majority of their Opinion-comments are positive. Except for McDonald’s that get a lot of high-intensity negative Opinion-comments even compared to the very similar fastfood restaurant Burger King. We are also able to gain access to the customer engagement behaviours, such as

Feedback-comments, that produce information that can be used by the companies. Overall the different

types of customer engagement behaviours provide a way to access the vast amounts of comments left

on company Facebook profiles.

81 of 80

10. Reference List

Adjei, M. T., Nowlin, E. L. and Ang, T. (2016) ‘The collateral damage of C2C communications on social networking sites: The moderating role of firm responsiveness and perceived fairness’, Journal of Marketing Theory and Practice. Routledge, 24(2), pp. 166–185. doi: 10.1080/10696679.2016.1131057.

Aggarwal, C. C. and Zhai, C. (2012) ‘A Survey of Text Classification Algorithms’, in Mining Text Data. Boston, MA: Springer US, pp. 163–222. doi: 10.1007/978-1-4614-3223-4_6.

Baesens, B. (2014) ‘Predictive analytics’, in Analytics in a Big Data World. Wiley, pp. 35–86. doi:

10.15358/0935-0381_2013_10_573.

Balagué, C. and de Valck, K. (2013) ‘Using Blogs to Solicit Consumer Feedback: The Role of

Directive Questioning Versus No Questioning’, Journal of Interactive Marketing. Elsevier B.V., 27(1), pp. 62–73. doi: 10.1016/j.intmar.2012.06.002.

Beckers, S. F. M., van Doorn, J. and Verhoef, P. C. (2018) ‘Good, better, engaged? The effect of company-initiated customer engagement behavior on shareholder value’, Journal of the Academy of Marketing Science. Journal of the Academy of Marketing Science, 46(3), pp. 366–383. doi:

10.1007/s11747-017-0539-4.

Bishop, C. M. (2006) Pattern Recognition and Machine Learning, Oxidation Communications.

Springer.

Bitter, S. and Grabner-Kräuter, S. (2016) ‘Consequences of customer engagement behavior: when negative Facebook posts have positive effects’, Electronic Markets. Electronic Markets, 26(3), pp.

219–231. doi: 10.1007/s12525-016-0220-7.

Blagus, R. and Lusa, L. (2013) ‘SMOTE for high-dimensional class-imbalanced data’, BMC Bioinformatics, 14(1), p. 106. doi: 10.1186/1471-2105-14-106.

Bolton, R. N. (2011) ‘Commentary. Customer Engagement: Opportunities and Challenges for Organizations’, Journal of Service Research, 14(3), pp. 272–274. doi: 10.1177/1094670511414582.

Boyle, T. (2019) Dealing with Imbalanced Data - Towards Data Science. Available at:

https://towardsdatascience.com/methods-for-dealing-with-imbalanced-data-5b761be45a18 (Accessed:

2 January 2020).

Bramer, M. (2016) Principles of Data Mining. Third Edit, Journal of the American Statistical

Association. Third Edit. London: Springer London (Undergraduate Topics in Computer Science). doi:

10.1007/978-1-4471-7307-6.

Brodie, R. J. et al. (2011) ‘Customer Engagement: Conceptual Domain, Fundamental Propositions, and Implications for Research’, Journal of Service Research, 14(3), pp. 252–271. doi:

10.1177/1094670511411703.

Brodie, R. J. et al. (2013) ‘Consumer engagement in a virtual brand community: An exploratory

82 of 80 analysis’, Journal of Business Research. Elsevier Inc., 66(1), pp. 105–114. doi:

10.1016/j.jbusres.2011.07.029.

Buckels, E. E., Trapnell, P. D. and Paulhus, D. L. (2014) ‘Trolls just want to have fun’, Personality and Individual Differences. Elsevier Ltd, 67, pp. 97–102. doi: 10.1016/j.paid.2014.01.016.

Burlutskiy, N. et al. (2016) ‘An Investigation on Online Vs. Batch Learning in Predicting User Behaviour’, in Reseach and Development in Intelligent Systems XXXIII, pp. 135–139.

Carlson, J. et al. (2018) ‘Customer engagement behaviours in social media: capturing innovation opportunities’, Journal of Services Marketing, 32(1), pp. 83–94. doi: 10.1108/JSM-02-2017-0059.

Carrizosa, E. and Romero Morales, D. (2013) ‘Supervised classification and mathematical optimization’, Computers and Operations Research. Elsevier, 40(1), pp. 150–165. doi:

10.1016/j.cor.2012.05.015.

Carvalho, J. P., Batista, F. and Coheur, L. (2012) ‘A critical survey on the use of Fuzzy Sets in Speech and Natural Language Processing’, in 2012 IEEE International Conference on Fuzzy Systems.

Brisbane, Australia: IEEE, pp. 270–277. doi: 10.1109/FUZZ-IEEE.2012.6250803.

Chakrabarti, S. (2003) Mining the Web - Discovering Knowledge from Hypertext Data. Edited by L.

Homet. Morgan Kaufmann Publishers.

Coles, B. A. and West, M. (2016) ‘Trolling the trolls: Online forum users constructions of the nature and properties of trolling’, Computers in Human Behavior. Elsevier Ltd, 60, pp. 233–244. doi:

10.1016/j.chb.2016.02.070.

Crammer, K. et al. (2006) ‘Online Passive-Aggresive Algorithms’, Journal of Machine Learning Research, 7, pp. 551–585. doi: 10.1201/b15810-63.

van Doorn, J. et al. (2010) ‘Customer Engagement Behavior: Theoretical Foundations and Research Directions’, Journal of Service Research, 13(3), pp. 253–266. doi: 10.1177/1094670510375599.

Einwiller, S. A. and Steilen, S. (2015) ‘Handling complaints on social network sites - An analysis of complaints and complaint responses on Facebook and Twitter pages of large US companies’, Public Relations Review. Elsevier Inc., 41(2), pp. 195–204. doi: 10.1016/j.pubrev.2014.11.012.

Erkan, I. and Evans, C. (2016) ‘The influence of eWOM in social media on consumers’ purchase intentions: An extended approach to information adoption’, Computers in Human Behavior. Elsevier Ltd, 61, pp. 47–55. doi: 10.1016/j.chb.2016.03.003.

Facebook (2018) Facebook Pages for marketing your business | Facebook Business, Facebook Business. Available at: https://www.facebook.com/business/products/pages (Accessed: 13 February 2019).

Fornacciari, P. et al. (2018) ‘A holistic system for troll detection on Twitter’, Computers in Human

Behavior. Elsevier, 89(March), pp. 258–268. doi: 10.1016/j.chb.2018.08.008.

83 of 80 Fournier, S. and Avery, J. (2011) ‘The uninvited brand’, Business Horizons. ‘Kelley School of

Business, Indiana University’, 54(3), pp. 193–207. doi: 10.1016/j.bushor.2011.01.001.

Ganesan, K. (2019) All you need to know about text preprocessing for NLP and Machine Learning.

Available at: https://www.kdnuggets.com/2019/04/text-preprocessing-nlp-machine-learning.html (Accessed: 25 November 2019).

Grant, M. and Kagan, J. (2019) Customer Service Definition, investopedia.com. Available at:

https://www.investopedia.com/terms/c/customer-service.asp (Accessed: 15 September 2019).

Groeger, L., Moroko, L. and Hollebeek, L. D. (2016) ‘Capturing value from non-paying consumers’

engagement behaviours: field evidence and development of a theoretical model’, Journal of Strategic Marketing. Routledge, 24(3–4), pp. 190–209. doi: 10.1080/0965254X.2015.1095223.

Gummerus, J. et al. (2012) ‘Customer engagement in a Facebook brand community’, Management Research Review. Edited by K. S. Coulter, 35(9), pp. 857–877. doi: 10.1108/01409171211256578.

Hansson, L., Wrangmo, A. and Søilen, K. S. (2013) ‘Optimal ways for companies to use Facebook as a marketing channel’, Journal of Information, Communication and Ethics in Society, 11(2), pp. 112–126.

doi: 10.1108/JICES-12-2012-0024.

Hartmann, J. et al. (2019) ‘Comparing automated text classification methods’, International Journal of Research in Marketing, 36(1), pp. 20–38. doi: 10.1016/j.ijresmar.2018.09.009.

Hastie, T., Tibshirani, R. and Friedman, J. (2009) The Elements of Statistical Learning. Second Edi.

New York, NY: Springer New York (Springer Series in Statistics). doi: 10.1007/b94608.

Haurum, H. (2018) CUSTOMER ENGAGEMENT BEHAVIOR IN THE CONTEXT OF CONTINUOUS SERVICE.

Hennig-Thurau, T. et al. (2004) ‘Electronic word-of-mouth via consumer-opinion platforms: What motivates consumers to articulate themselves on the Internet?’, Journal of Interactive Marketing.

Elsevier, 18(1), pp. 38–52. doi: 10.1002/dir.10073.

Hennig-Thurau, T. et al. (2010) ‘The Impact of New Media on Customer Relationships’, Journal of Service Research, 13(3), pp. 311–330. doi: 10.1177/1094670510375460.

Hollebeek, L. D., Glynn, M. S. and Brodie, R. J. (2014) ‘Consumer Brand Engagement in Social Media: Conceptualization, Scale Development and Validation’, Journal of Interactive Marketing.

Elsevier B.V., 28(2), pp. 149–165. doi: 10.1016/j.intmar.2013.12.002.

Hotten, R. (2015) Volkswagen: The scandal explained - BBC News, BBC News. Available at:

https://www.bbc.com/news/business-34324772 (Accessed: 28 May 2020).

Jaakkola, E. and Alexander, M. (2014) ‘The Role of Customer Engagement Behavior in Value Co-Creation’, Journal of Service Research, 17(3), pp. 247–261. doi: 10.1177/1094670514529187.

Jacob van Veen, H., Nguyen The Dat, L. and Segnini, A. (2015) Kaggle Ensembling Guide | MLWave.

84 of 80 Available at: https://mlwave.com/kaggle-ensembling-guide/#comment-333091 (Accessed: 20 April 2020).

James, G. et al. (2013) An Introduction to Statistical Learning with Applications in R. Edited by G.

Casella, S. Fienberg, and I. Olking. New York, NY: Springer New York (Springer Texts in Statistics).

doi: 10.1007/978-1-4614-7138-7.

Jurafsky, D. and Martin, J. H. (2008) Speech and language processing, 2. Edition. 2. Edition, Prentice Hall. 2. Edition.

Jurafsky, D. and Martin, J. H. (2018) Speech and Language Processing. Third Edit. Available at:

https://web.stanford.edu/~jurafsky/slp3/.

Kentish, B. (2017) HSBC funding destruction of vast areas of Indonesian rainforest, new report claims

| The Independent. Available at: https://www.independent.co.uk/news/world/asia/hsbc-rainforest-deforestation-indonesia-funding-claims-report-a7529761.html (Accessed: 29 May 2020).

Kharpal, A. (2016) Samsung’s Galaxy Note 7 phones caught fire because of the ‘aggressive’ battery design: Report. Available at: https://www.cnbc.com/2016/12/06/samsung-galaxy-note-7-phones-caught-fire-because-of-the-aggressive-battery-design-report.html (Accessed: 28 May 2020).

King, R. A., Racherla, P. and Bush, V. D. (2014) ‘What We Know and Don’t Know About Online Word-of-Mouth: A Review and Synthesis of the Literature’, Journal of Interactive Marketing. Elsevier B.V., 28(3), pp. 167–183. doi: 10.1016/j.intmar.2014.02.001.

Kumar, V. et al. (2010) ‘Undervalued or Overvalued Customers: Capturing Total Customer Engagement Value’, Journal of Service Research, 13(3), pp. 297–310. doi:

10.1177/1094670510375602.

Kumar, V. and Pansari, A. (2016) ‘Competitive Advantage through Engagement’, Journal of Marketing Research, 53(4), pp. 497–514. doi: 10.1509/jmr.15.0044.

Lemaitre, G. et al. (no date) Comparison of the different over-sampling algorithms — imbalanced-learn 0.5.0 documentation. Available at:

https://imbalanced-

learn.readthedocs.io/en/stable/auto_examples/over- sampling/plot_comparison_over_sampling.html#sphx-glr-auto-examples-over-sampling-plot-comparison-over-sampling-py (Accessed: 19 April 2020).

Liu, H. et al. (2019) ‘A Fuzzy Approach to Text Classification with Two-Stage Training for

Ambiguous Instances’, IEEE Transactions on Computational Social Systems. IEEE, 6(2), pp. 227–240.

doi: 10.1109/TCSS.2019.2892037.

Liu, H. and Cocea, M. (2017) ‘Fuzzy rule based systems for interpretable sentiment analysis’, in 2017 Ninth International Conference on Advanced Computational Intelligence (ICACI). IEEE, pp. 129–136.

doi: 10.1109/ICACI.2017.7974497.

Ljungberg, B. F. (2017) ‘Dimensionality reduction for bag-of-words models: PCA vs LSA’, pp. 1–6.

Available at: https://pypi.python.org/pypi/Gutenberg.

85 of 80 Lu, J., Zhao, P. and Hoi, S. C. H. (2016) ‘Online Passive-Aggressive Active learning’, Machine

Learning. Springer US, 103(2), pp. 141–183. doi: 10.1007/s10994-016-5555-y.

Manning, C. D. et al. (2009) ‘Text classification and Naive Bayes’, in Introduction to Information Retrieval, pp. 234–265. doi: 10.1017/cbo9780511809071.014.

Manning, C. D., Raghavan, P. and Schütze, H. (2009) An Introduction to Information Retrieval. Online Edi. Available at: http://www-nlp.stanford.edu/IR-book/.

Mishu, S. Z. and Rafiuddin, S. M. (2018) ‘Performance analysis of supervised machine learning algorithms for text classification’, 19th International Conference on Computer and Information Technology, ICCIT 2016, (December), pp. 409–413. doi: 10.1109/ICCITECHN.2016.7860233.

van Noort, G. and Willemsen, L. M. (2012) ‘Online Damage Control: The Effects of Proactive Versus Reactive Webcare Interventions in Consumer-generated and Brand-generated Platforms’, Journal of Interactive Marketing. Elsevier B.V., 26(3), pp. 131–140. doi: 10.1016/j.intmar.2011.07.001.

Okazaki, S. et al. (2015) ‘Using Twitter to engage with customers: a data mining approach’, Internet Research, 25(3), pp. 416–434. doi: 10.1108/IntR-11-2013-0249.

Paul, M. (2018) Multiclass and Multi-label Classification. Available at:

https://cmci.colorado.edu/classes/INFO-4604/files/slides-7_multi.pdf (Accessed: 2 April 2020).

Pedregosa, F. et al. (2011a) Scikit-learn: Machine Learning in Python. 1.4. Support Vector Machines

— scikit-learn 0.22.2 documentation. Available at: https://scikit-learn.org/stable/modules/svm.html (Accessed: 1 May 2020).

Pedregosa, F. et al. (2011b) Scikit-learn: Machine Learning in Python. 1.5. Stochastic Gradient Descent — scikit-learn 0.22.2 documentation. Available at:

https://scikit-learn.org/stable/modules/sgd.html (Accessed: 7 April 2020).

Pedregosa, F. et al. (2011c) Scikit-learn: Machine Learning in Python. 1.9. Naive Bayes — scikit-learn 0.22.2 documentation. Available at: https://scikit-learn.org/stable/modules/naive_bayes.html#out-of-core-naive-bayes-model-fitting (Accessed: 10 March 2020).

Pedregosa, F. et al. (2011d) Scikit-learn: Machine Learning in Python. 3.3. Metrics and scoring:

quantifying the quality of predictions. Available at:

https://scikit-learn.org/stable/modules/model_evaluation.html#precision-recall-f-measure-metrics (Accessed: 21 April 2020).

Pedregosa, F. et al. (2011e) Scikit-learn: Machine Learning in Python. 6.2. Feature Extraction.

Available at: https://scikit-learn.org/stable/modules/feature_extraction.html#text-feature-extraction (Accessed: 18 April 2020).

Pedregosa, F. et al. (2011f) Scikit-learn: Machine Learning in Python.

sklearn.linear_model.LogisticRegression — scikit-learn 0.22.1 documentation. Available at:

https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html

(Accessed: 25 February 2020).

86 of 80 Pedregosa, F. et al. (2011g) Scikit-learn: Machine Learning in Python. sklearn.svm.LinearSVC — scikit-learn 0.22.2 documentation. Available at:

https://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html (Accessed: 2 April 2020).

Rennie, J. D. M. et al. (2003) ‘Tackling the Poor Assumptions of Naive Bayes Text Classifiers’, Proceedings, Twentieth International Conference on Machine Learning, 2(1973), pp. 616–623.

Roberts, C. and Alpert, F. (2010) ‘Total customer engagement: designing and aligning key strategic elements to achieve growth’, Journal of Product & Brand Management, 19(3), pp. 198–209. doi:

10.1108/10610421011046175.

Roy, S. K. et al. (2018) ‘Customer engagement behavior in individualistic and collectivistic markets’, Journal of Business Research, 86(October 2016), pp. 281–290. doi: 10.1016/j.jbusres.2017.06.001.

Saunders, M., Lewis, P. and Thornhill, A. (2009) Research Methods for Business Students. Fifth Edit.

Pearson Education Limited.

Schamari, J. and Schaefers, T. (2015) ‘Leaving the Home Turf: How Brands Can Use Webcare on Consumer-generated Platforms to Increase Positive Consumer Engagement’, Journal of Interactive Marketing. Marketing EDGE.org., 30, pp. 20–33. doi: 10.1016/j.intmar.2014.12.001.

Serva, C. (2015) Positivism in Sociology: Definition, Theory & Examples - Video & Lesson Transcript

| Study.com. Available at: https://study.com/academy/lesson/positivism-in-sociology-definition-theory-examples.html (Accessed: 14 April 2020).

Silge, J. and Robinson, D. (2019) Text Mining with R - A Tidy Approach. Available at:

https://www.tidytextmining.com/index.html (Accessed: 28 January 2020).

Smolyakov, V. (2017) Ensemble Learning to Improve Machine Learning Results. Available at:

https://blog.statsbot.co/ensemble-learning-d1dcd548e936 (Accessed: 20 April 2020).

Statista (2020) Most popular social networks worldwide as of July 2018, ranked by number of active users (in millions), Statista.Com. Available at: https://www.statista.com/statistics/272014/global-social-networks-ranked-by-number-of-users/ (Accessed: 19 February 2019).

Swamynathan, M. (2017) Mastering Machine Learning with Python in Six Steps, Mastering Machine Learning with Python in Six Steps. doi: 10.1007/978-1-4842-4947-5.

Tfidf.com (no date). Available at: http://www.tfidf.com/ (Accessed: 19 December 2019).

Thangaraj, M. (2018) ‘Text Classification Techniques: A Literature Review’, Interdisciplinary Journal of Information, Knowledge, and Management, 13, pp. 117–135. doi: 10.28945/4066.

Tiago, M. T. P. M. B. and Veríssimo, J. M. C. (2014) ‘Digital marketing and social media: Why bother?’, Business Horizons, 57(6), pp. 703–708. doi: 10.1016/j.bushor.2014.07.002.

Twitter (2019) How to use hashtags. Available at:

https://help.twitter.com/en/using-twitter/how-to-use-hashtags (Accessed: 17 December 2019).

In document Customer Engagement Behaviours in Facebook Comments (Sider 79-88)