소셜미디어 콘텐츠 주제와 고객 인게이지먼트 간의 관계분석: 머신러닝 방법론을 중심으로

다국어 초록 (Multilingual Abstract)

Customer engagement is regarded as a performance indicator of social media marketing, and previous studies have reported that the characteristics of content to increase customer engagement. However, the topic of content has not been sufficiently studied. This study analyzes the relationship between the topic of social media content and customer engagement and suggests an analysis procedure that can apply a machine learning model, a key tool for recent digital transformation. For empirical analysis, 154,705 social media data of 51 global brands were collected, and content topics were classified using a topic modeling method. And the relationship between content topic and customer engagement was analyzed using zero-inflated negative binomial regression analysis and machine learning model. As a result of the analysis, contents of 51 brands were classified into 18 contents topics, and there was a difference in the impact on customer engagement according to the topic. In addition, using a machine learning model, it was possible to predict the customer engagement performance of the content with an accuracy of about 90%. This study contributed to the marketing literature by analyzing the relationship between social media content topics and customer engagement through machine learning methodology.

참고문헌 (Reference)

1 Chen, T., "Xgboost:A scalable tree boosting system" 785-794, 2016

2 Berger, J., "What makes online content viral?" 49 (49): 192-205, 2012

3 Araujo, T., "What Motivates Consumers To Re-Tweet Brand Content? : The impact of information, emotion, and traceability on pass-along behavior" 55 (55): 284-295, 2015

4 Okazaki, S., "Using Twitter to engage with customers : a data mining approach" 25 (25): 416-434, 2015

5 Aleti, T., "Tweeting with the stars : Automated text analysis of the effect of celebrity social media communications on consumer word of mouth" 48 (48): 17-32, 2019

6 Guo, T., "The effect of information disclosure on industry payments to physicians"

7 Lessmann, S., "Targeting customers for profit: An ensemble learning framework to support marketing decision-making" 2019

8 Kumar, V., "Synergistic effects of social media and traditional marketing on brand sales : capturing the timevarying effects" 45 (45): 268-288, 2017

9 Friedman, J. H., "Stochastic gradient boosting" 38 (38): 367-378, 2002

10 Samuel, A. L., "Some studies in machine learning using the game of checkers" 3 (3): 210-229, 1959

11 Büschken, J., "Sentencebased text analysis for customer reviews" 35 (35): 953-975, 2016

12 Vermeer, S. A., "Seeing the wood for the trees : How machine learning can help firms in identifying relevant electronic word-ofmouth in social media" 36 (36): 492-508, 2019

13 Kanuri, V. K., "Scheduling content on social media : Theory, evidence, and application" 82 (82): 89-108, 2018

14 Chawla, N. V., "SMOTE : synthetic minority over-sampling technique" 16 : 321-357, 2002

15 Breiman, L., "Random forests" 45 (45): 5-32, 2001

16 Azagba, S., "Psychosocial working conditions and the utilization of health care services" 11 (11): 1-7, 2011

17 Anandarajan, M., "Probabilistic topic models, In Practical Text Analytics" Springer 117-130, 2019

18 Cui, D., "Prediction in marketing using the support vector machine" 24 (24): 595-615, 2005

19 De Vries, L., "Popularity of brand posts on brand fan pages : An investigation of the effects of social media marketing" 26 (26): 83-91, 2012

20 Zhang, Y., "Modeling the role of message content and influencers in social media rebroadcasting" 34 (34): 100-119, 2017

21 Jacobs, B. J., "Model-based purchase predictions for large assortments" 35 (35): 389-404, 2016

22 Ling, X., "Model ensemble for click prediction in bing search ads" 689-698, 2017

23 Tirunillai, S., "Mining marketing meaning from online chatter : Strategic brand analysis of big data using latent dirichlet allocation" 51 (51): 463-479, 2014

24 Blei, D. M., "Latent dirichlet allocation" 3 : 993-1022, 2003

25 Liu, X., "Large-scale cross-category analysis of consumer review content on sales conversion leveraging deep learning" 56 (56): 918-943, 2019

26 Li, Y., "Is a picture worth a thousand words? An empirical study of image content and social media engagement" 57 (57): 1-19, 2020

27 Muntinga, D. G., "Introducing COBRAs : Exploring motivations for brand-related social media use" 30 (30): 13-46, 2011

28 Toubia, O., "Intrinsic vs. image-related utility in social media : Why do people contribute content to twitter?" 32 (32): 368-392, 2013

29 Göçken, M., "Integrating metaheuristics and artificial neural networks for improved stock price prediction" 44 : 320-331, 2016

30 Batra, R., "Integrating marketing communications : New findings, new lessons, and new ideas" 80 (80): 122-145, 2016

31 Malhotra, A., "How to get your messages retweeted" 53 (53): 61-66, 2012

32 Swani, K., "Evaluating Facebook brand content popularity for service versus goods offerings" 79 : 123-133, 2017

33 Heath, C., "Emotional selection in memes : the case of urban legends" 81 (81): 1028-1041, 2001

34 Greene, W. H., "Econometric analysis" Pearson Education India 2003

35 Ballestar, M. T., "Customer segmentation in e-commerce : Applications to the cashback business model" 88 : 407-414, 2018

36 Pansari, A., "Customer engagement : the construct, antecedents, and consequences" 45 (45): 294-311, 2017

37 Brodie, R. J, "Customer engagement : Conceptual domain, fundamental propositions, and implications for research" 14 (14): 252-271, 2011

38 Trusov, M., "Crumbs of the cookie : User profiling in customer-base analysis and behavioral targeting" 35 (35): 405-426, 2016

39 Tsai, C. F., "Credit rating by hybrid machine learning techniques" 10 (10): 374-380, 2010

40 Huang, D., "Consumer preference elicitation of complex products using fuzzy support vector machine active learning" 35 (35): 445-464, 2016

41 Jalali, N. Y., "Composing tweets to increase retweets" 36 (36): 647-668, 2019

42 Hartmann, J., "Comparing automated text classification methods" 36 (36): 20-38, 2019

43 Hoffman, D. L., "Can you measure the ROI of your social media marketing?" 52 (52): 41-49, 2010

44 Seetharaman, P., "Business models shifts : Impact of Covid-19" 54 : 102173-, 2020

45 Breiman, L., "Bagging predictors" 24 (24): 123-140, 1996

46 Chakraborty, I., "Attribute Sentiment Scoring with Online Text Reviews: Accounting for Language Structure and Attribute Self-Selection" 2019

47 Cruz, J. A., "Applications of machine learning in cancer prediction and prognosis" 2 : 117693510600200030-, 2006