Abstract
This article aims to explore the evolution of social network in marketing research by analyzing the co-occurrence index and network structures of keywords. We find that the number of articles which subjective tittle consist of social networks within 19 marketing journals and 9 UTD (Utdallas list of top journals) management journals increase significantly and the number of keywords whose frequency are no less than two also grow dramatically since 2010, the network structures of keywords 2010–2014 become more dispersed shows as most of keywords’ centralities are between 0.32 and 0.63, and more keywords have strong relationships (Higher Cosine Index) with social networks or networks than 2001–2009. We also conclude that social network analysis has been mainly applied to study relationships, diffusion, influence, customer analysis, and enterprise management five subfields. Since mobile internet, intelligent devices, new media and digital technology are developing rapidly, social networks will be a powerful tool to study the related research fields.
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
Introduction
Social network analysis has been used in innovation management (Obstfeld 2005), alliance collaboration strategy (Lazzarini 2007), organizational structure analysis (Park and Luo 2001), social influence analysis (Lowrey et al. 2004; Watts and Dodds 2007) and other research fields. Previous research has studied the social networks characteristics relations, ties, and composition (Garton et al. 1997), centrality in social networks (Freeman et al. 1980), the difference between social networks and other types of networks (Newman and Park 2003). Furthermore, prior study provides several methods for measuring social networks (Bernard et al. 1990), and models of social networks (Anderson et al. 1999; Hunter 2007; Pattison and Robins 2002; Robins et al. 2007).
As the number of social networking sites increases dramatically, more and more people create online profiles and share personal information with network-friends(Gross and Acquisti 2005). That provides more chance for marketing researchers to understand consumers. Social network analysis is one of the major paradigms in contemporary sociology (Wikipedia 2014), which has been used in marketing research frequently, but no research has studied the evolution of social networks in marketing research, so this article try to analyze the changes of social networks used in marketing research since 2001–2014, and find out the main research points and the development tendency.
This article is organized as follows: Part 2, we introduce the theoretical background. Part 3, we address the explanation of method and data collection. Part 4, we compare the changes of social network structures between 2001–2009 and 2010–2014, and point out the hot research topics in the past 14 years. Part 5, we discuss the conclusions and the limitations.
Literature review
Social networks and marketing
Social networks are familiar to marketing researchers and have been widely used in marketing research. They have been applied to study consumer behaviors e.g. customer preference (Yang and Allenby 2003), leadership influence (Kratzer and Lettl 2009; Godes 2011), new production adoption (Hu and Van den Bulte 2014), individual behavior prediction (Goel and Goldstein 2013) etc. social network reflects the connections and relationships among different ties, it evolves with new ties’ generation and old ties’ disappearance, and the changes of social network structures also have effects on ties’ movements. Marketing activities usually put more emphasis on relationships effectiveness, e.g. peer to peer (Bhatia and Wang 2011; Lin et al. 2013; Aral and Walker 2011), virtual communities (Dholakia et al. 2004; Bélisle and Bodur 2010), and B2B relationships (Wuyts et al. 2009) etc.
Social networks often appear in marketing research; they not only reflect the social structure of relationships, but also a research paradigm of social analysis. With the growth of social networking websites, social communities, and non-profit organizations, the social relationships will become more and more complex, and this must have a great effect on marketing activities and research.
Marketing research
Marketing research is one of the most important parts of marketing; it attracts both academy researchers and marketing directors’ attentions. Several hot citied books and journal articles provide strategy and tactics of marketing research (Green and Tull 1970), principles of marketing research (Bagozzi 1994), methodological foundations (Iacobucci and Churchill 2009). In the book Marketing Research, Aaker et al. (2008) summary the marketing research methodologies, point out their limitations, and analyze the relevance between marketing intelligence and research forefront, such as the Internet power.
There are so many methods have been used in marketing research, for example structural equation modeling (SEM) which is widely used in marketing and consumer research (Baumgartner and Homburg 1996), Hair et al. (2012) assess the use of partial least squares structural equation modeling (PLS-SEM) and provide guidance on preventing common pitfalls. Prior research also shows that the applications of SEM are popular and have formed standard criteria. Conversely, although social networks has been widely used in marketing research, little attention has been paid to summary the development process and no articles have analyze the changes of research topics of social networks applied in marketing research. So we want to fill this gap, compare the research topics changes, summary the development trends, find out the relative degree of different research points and social networks, and predict the future research tendency and hot topics.
Method and data collection
Method
Co-word analysis
Co-word analysis is a quantitative technique to comb literatures and find the interrelationships of science (He 1999). Since last century, co-word analysis has already been implemented by lots of researchers and research groups. As it is easy to operate, it has been used to evaluate R&D impacts (Kostoff 1993), examine the trends of technological development (Wu and Leu 2014), analyze the research trends (Dehdarirad et al. 2014), find hotpots of research (Wang et al. 2014a) and summary research topics evolution (Wang et al. 2014b). Co-word, like co-citation and co-author analysis is carried by exploring co-occurrence and co-absence of keywords (Ronda-Pupo and Guerras-Martin 2012). We use co-word analysis to analyze the evolution of social networks used in marketing research, and find out the interrelationships of keywords.
Co-word analysis uses co-occurrence matrix of keywords as input (Salton and McGill 1983; Ronda-Pupo and Guerras-Martin 2012). We also use co-occurrence matrix as input data, and then calculate the inclusion index of each pair of keywords, but a little different from the way of Ronda-Pupo and Guerras-Martin (2012) calculate the inclusion index as formula I ij = C ij /Min (C i , C j ). We calculate cosine index I ij the same as Salton and McGill (1983) and Leydesdorff (2008) as formula \(I_{ij} = C_{ij} /\sqrt {C_{i} \times C_{j} }\) which consists of both the number of keywords i and j not the minimum one (I ij is the times of co-occurrence of keywords i and j, C i is the appearing times of keyword i, C j is the appearing times of keyword j, Min (C i , C j ) is the minimum of the appearing times of keywords i and j).
Social network analysis
Based on the co-occurrence matrixes, we use social network analysis method to map the network structures and analyze the interrelationships evolution of keywords between the two stages 2001–2009 and 2010–2014. And then, we calculate the centrality of each vector (keyword) by the same software (Pajek) and the same algorithms as Ronda-Pupo and Guerras-Martin (2012). We also range the centrality value with 0.00–0.95 and choose three thresholds 0.31, 0.63 and 0.95, the network periphery 0.00–0.31, the semi-periphery 0.32–0.63 and the core of the networks 0.64–0.95 (Ronda-Pupo and Guerras-Martin 2012). Next, we locate the all keywords (frequency no less than two) into different thresholds based on the centrality value, and analyze the evolution trends of each keyword in the prior research and compare the changes of hot topics between 2001–2009 and 2010–2014.
Data collection
We collect articles on social networks with top 4 marketing journals Journal of Marketing (JOM), Marketing Science (MS), Journal of Marketing Research (JMR) and Journal of Consumer Research (JCR), and other 15 important marketing related journals International Journal of Research in Marketing (IJRM), Marketing Letters (ML), Industrial Marketing Management (IMM), International Journal of Market Research (IJMR), Journal of Service Management (JSM), Journal of International Marketing (JIM), Psychology and Marketing (PM), Journal of Service Research (JSR), Journal of Advertising Research (JAR), Journal of Services Marketing (JSM), Journal of the Academy of Marketing Science (JAMS), Journal of Consumer Psychology (JCP), Journal of Advertising (JOA), Managing Service Quality (MSQ), Journal of Retailing (JOR). We also collect social networks and marketing-related articles on the journals Management Science (MS), Organization Science (OS), Academy of Management Journal (AMJ), Information Systems Research (ISR), Strategic Management Journal (SMJ), Administrative Science Quarterly (ASQ), Production and Operations Management (POM), MIS Quarterly (MISQ), Journal of Operations Management (JOM). We search the web of science database provided by Thomson Reuters and the published year with 2001 and 2014 and the query result shows as Fig. 1.
We find the number of published articles of marketing journalsFootnote 1 increased significantly since 2010, so we separate the data into two stages: 2001–2009 and 2010–2014. In order to be consistent with the stages of marketing journals, we segment the management journals with the same time points, although the number of published articles increased to 10 and never fell below since 2011. And then, we calculate the total number of the two stages of top 4, 15 important marketing journals and 9 management journals, the detail shows as Fig. 2.
After the stage separation, we begin to count the number of original keywords which have been processed, and the results list in Table 1.
In order to facilitate the co-word analysis, we use the most frequently occurring keywords as the theme words/phrases to frequency statistics as He (1999) did. We also process the keywords with the same core-word but different forms (nouns, verbs, and adjectives; singular and plural) into unique form, such as we transform networking/network to networks and count the frequency of networks to co-word analysis. After the word processing, we get 59 keywords of top 4, 147 of other important journals and 255 of the 9 UTD management journals in stage 1; and 195 of top 4, 438 of other important journals and 311 of the 9 UTD management journals in stage 2.
Analysis and results
Deconstruction evolution of keywords
In this section, we analyze the frequency of keywords (see Table 2). This shows the dispersion change of keywords in different stages, and the percentages of low frequency keywords are higher than Furrer et al. (2008) and Ronda-Pupo and Guerras-Martin (2012) who found about 65 % keywords appeared only once. We find that the number of higher frequency keywords increases from stage 1 to stage 2 within marketing journals, but it decreases in UTD management journals. The appearing times of keywords whose frequency are no less than 2 account for 20.59, 23.70 and 56.86 % proportions of the total appearing times in stage 1, and 39.15, 43.05 and 39.83 % in stage 2 of top 4, other important marketing journals and UTD management journals, and the distribution of parts of higher frequency keywords shows in Table 3.
In stage 1 the frequency of keywords is much lower than stage 2 within marketing journals, but for UTD management journals change a little. By analyzing the frequency of keywords, the number of higher frequency keywords increases dramatically within marketing journals which reflects the research fields of social networks in marketing research becomes wider in the last 5 years. Of course, some research topics keep popular since 2001, such as ‘innovation’ and ‘word of mouth’. Furthermore, some new research fields attract more attention of researchers in stage 2 (e.g. social media), consistent with the social media utilization in marketing activities of enterprises, more and more enterprises use social media to practice their marketing plans.
Comparing marketing journals and UTD management journals, we find a significant difference. Marketing journals usually focus on consumer-level research, but UTD management journals mainly aim to study organization/enterprise-level, such as marketing journal published more articles about word of mouth how to affect consumers’ behavior (e.g. Kozinets et al. 2010), UTD management journals usually put more emphasis on marketing/market strategy of enterprise-level (e.g. Chellappa and Saraf 2010).
Network structure analysis
Top 4
In stage 1, only five keywords’ frequency is no less than two, but the number increases to 24. The number of keywords directly link to social networks changes from 3 to 19, the keywords ‘word of mouth’, ‘social contagion’ and ‘diffusion of innovations’ have a high co-occurrence frequency 5 in stage 2, and the cosine index value are 0.29, 0.36 and 0.40. In stage 1 the cosine index value between ‘innovation’, ‘word of mouth’, ‘diffusion of innovation’, and ‘social networks’ are 0.25, 0.71, and 0.37, it means ‘word of mouth’ and ‘social networks’ are strong related in both of the two stages. By analyzing Fig. 3, we find social networks in the core position within stage 1 and stage 2, which becomes more significant in stage 2, and the degrees of vertices are hierarchical, ‘social networks’ in the center, ‘word of mouth’, ‘service’, ‘social media’, ‘homphily’, ‘contagion’ and ‘social contagion’ whose degrees are no less than 5 are in the second level, the others whose degrees are less than 5 in the third level (e.g. e-commerce, social influence, innovation etc.), the zero degree vertices ‘social capital’ and ‘market orientation’ are on the edge. It helps us to grab the hot research points in the last 5 years.
Other important marketing journals
Figure 4 shows that the network structure change dramatically. Firstly, the number of vertices increases from 14 to 82, the number of lines changes from 14 to 258. Secondly, the number of isolated vertices decreases from 3 (China, innovation, and interfirm relationships) to 2 (network embeddedness and stakeholders). The number of vertices which are directly link to social networks/networks grows significantly that to a large extent reflects the related research fields become more and more popular, and ‘social networks/networks’ takes the central palace, but ‘word of mouth’ has a direct link with ‘social networks’ in the two stages, and the cosine index are no less than 0.2 (0.32 in stage 1, 0.25 in stage 2) which reflects using social network to study word of mouth effects is still a hot research point.
Thirdly, in order to find out the relationships strength of the ties, we calculate the cosine index of stage 2 to analyze the relationships between social networks/networks and the other keywords (see Table 4). The cosine index of seven keyword groups are more than 0.30, they are networks-innovation, social networks-brand, networks-interaction, social networks-community, networks-relationships, social networks-customer retention, and networks-small and medium sized enterprises (SMEs); which shows the invisible strong relationships of the network structure. For the keywords in Table 4 are higher frequency ones, so the strong related keyword groups mean higher focus of researchers. Furthermore, the degree distribution of vertices is also hierarchical, the number of high degree vertices is much more than stage 1 (e.g. service, innovation, brand, and social capital), to a large extent, it explains the change of research topics.
UTD management journals
The result of comparing marketing journals and UTD management journals shows a great difference. First, the number of vertices decreases from 57 to 48, and the total number of lines also decreases from 406 to 174 from stage 1 to stage 2. Second,the network has much more vertices than marketing journals in stage 1, and 10 vertices neither link to social networks nor networks (e.g. governance, management, emerging markets and so on, see Fig. 5, stage 1). Third, the strong related keyword group whose cosine index are more than 0.30 and link directly to social networks or networks in stage 1: embeddedness-networks (0.33), innovation-social networks (0.42), entrepreneurship-networks (0.32), identity- networks (0.41), capabilities- social networks (0.32); stage 2: market-networks (0.35), innovation-networks (0.33), performance-networks (0.38), organizations-networks (0.34), social structure-networks (0.56), embeddedness-networks (0.34), ties-networks (0.58), randomized experiment-social networks (0.41), peer influence-social networks (0.50), social contagion-social networks (0.41), homophily-social networks (0.33), viral marketing-social networks (0.41), e-commerce-social networks (0.41); comparing with stage 1, there are more keywords have strong relationships with social networks/networks, which reflects the research topics become dispersed.
Centrality analysis
The centrality reflects the relative importance of vertices within the networks. We study the evolution of networks by comparing the degree centrality of stage 1 and stage 2. In our research, the networks are directed and co-appearance times regard as the value of lines, and the results show three trends:
-
1.
The total number of core position keywords decreases among all of the journals, especially UTD management journals from 10 to 0. It means that the relative importance of vertices falls down; most of the core position keywords lost their central place.
-
2.
The percentage of semi-periphery position keywords grows significantly, from 40.00, 6.67, and 82.46 % to 87.50, 84.15 and 91.67 % among the three kinds of journals. This is mainly due to an increasing number of the subfields of research, e.g. viral marketing, brand equity, agent-based model and so on. In addition, it refers to the research fields are becoming diversified.
-
3.
The total number of periphery position keywords changes a little, but the keywords are different between the two stages. Partly because of the emergence of new subfields of research, on the other hand, some keywords move to semi-periphery positions, e.g. China, business networks, business relationships and so on. So the periphery vertices always keep a high speed of changing.
Table 5 depicts the changing process of the keywords’ centralities; we can illustrate the evolution of network structures. The keywords ‘social networks’ or ‘networks’ own a higher centrality score, which shows that they are more important than other keywords within the networks especially in stage 2. Recent five years, the number of subfields related to social networks in marketing research grows rapidly, and most of them in the semi-periphery area such as viral marketing, brand equity, and agent-based model etc. However, some traditional research topics always attract more attention, e.g. word of mouth, innovation, social capital, relationships and so on. So social networks not only are widely used in new research fields but also traditional ones.
Networks evolution within the two stages
In order to study the evolution of the networks, we use network clustering coefficient and density to analyze the evolution process. Network clustering coefficient and density are used to measure the distance or similarity among the vertices of networks. Network clustering coefficient refers the possibility of two vertices which have a common neighbor are directly linked, density reflects the internal coherence or strengths of the relationships among vertices (Ronda-Pupo and Guerras-Martin 2012). We also use Pajek (info → network → general) to calculate the two index (see Table 6). Comparing the two indexes between stage 1 and stage 2, we find both of them are descent, the results are opposite to Ronda-Pupo and Guerras-Martin (2012). The reason why is that Ronda-Pupo and Guerras-Martin used social networks to study the concept evolution of strategy, but we analyze the changing of research fields, one concept will form a more and more consistent understanding, yet one research method or paradigm will be used in more and more research fields. Our results coincide with the cosine index matrix, one hand, the number of high frequency keywords increase; the other hand, the keyword groups with higher cosine index grow significantly.
Conclusion
In the period 2001–2014, social network has been used as a powerful tool in marketing research. Through analyzing the keywords of 421 articles in 28 journals, we find social networks has usually been applied to study relationships (e.g. business relationships, organizational relationships, commercial friendships, and customer relationships), diffusion (e.g. diffusion of innovations, diffusion of knowledge and diffusion models), influence (e.g. social influence and peer influence), customer analysis (e.g. customer value, customer loyalty, customer satisfaction, customer behavior, and customer lifetime value etc.), and enterprise management (e.g. firm performance, strategic alliances, internationalization, R&D, competition, business strategy, marketing, brand management and so on). In addition, with the increasing utility of social media in marketing activities, social networks has formed a strong relationship with social media, and it will be widely applied to study social media effects and activities.
Since mobile internet, intelligent devices, new media and digital technology have a great impact on marketing activities, and they will attract more attention of marketing directors and scholars, as well social networks has great advantages to study how they work and their effects. So in the future, social networks will be popular applied to study media effects, function mechanism of new technology/devices, and social influence of mobile internet. After all, social networks method takes an important place of relationships and influence research, it a good choice for using social networks to study the related fields.
One contribution of our study is using co-word analysis to analyze the evolution of social networks used in marketing research, and this method proves to be effective. Second, we separate the journals into three kinds and compare their similarities and dissimilarities which are different from the prior research (e.g. Liu et al. 2012; Muñoz-Leiva et al. 2012). Third, we point the changing process of hot research topics, and summarize the main research fields of social networks related in marketing research. Finally, we predict some research points which will be popular in the near future.
Of course, our study also has limitations. Firstly, we just select 19 marketing journals and 9 UTD management journals which take a lower proportion of all related journals, so the results maybe neglect some research topics. Secondly, only using keywords to analyze the research trends maybe not enough, next we will use full text analysis to deeply study the research trends of social networks in marketing research. At last, we expect our study can provide giddiness for marketing research with social networks method, and more scholars apply social networks to solve marketing problems.
Notes
That means the total number of top 4 and other 15 important marketing journals, so the number of article increase from around 20 to over 30 and never fell below 30.
References
Aaker, D. A., Kumar, V., & Day, G. S. (2008). Marketing research. Hoboken: Wiley.
Anderson, C. J., Wasserman, S., & Crouch, B. (1999). A p* primer: logit models for social networks. Social Networks, 21(1), 37–66.
Aral, S., & Walker, D. (2011). Creating social contagion through viral product design: A randomized trial of peer influence in networks. Management Science, 57(9), 1623–1639.
Bagozzi, R. P. (Ed.). (1994). Principles of marketing research (pp. 317–385). Cambridge, Oxford, Mass: Blackwell.
Baumgartner, H., & Homburg, C. (1996). Applications of structural equation modeling in marketing and consumer research: A review. International Journal of Research in Marketing, 13(2), 139–161.
Bélisle, J. F., & Bodur, H. O. (2010). Avatars as information: Perception of consumers based on their avatars in virtual worlds. Psychology and Marketing, 27(8), 741–765.
Bernard, H. R., Johnsen, E. C., Killworth, P. D., McCarty, C., Shelley, G. A., & Robinson, S. (1990). Comparing four different methods for measuring personal social networks. Social Networks, 12(3), 179–215.
Bhatia, T., & Wang, L. (2011). Identifying physician peer-to-peer effects using patient movement data. International Journal of Research in Marketing, 28(1), 51–61.
Chellappa, R. K., & Saraf, N. (2010). Alliances, rivalry, and firm performance in enterprise systems software markets: A social network approach. Information Systems Research, 21(4), 849–871.
Dehdarirad, T., Villarroya, A., & Barrios, M. (2014). Research trends in gender differences in higher education and science: A co-word analysis. Scientometrics, 101(1), 273–290.
Dholakia, U. M., Bagozzi, R. P., & Pearo, L. K. (2004). A social influence model of consumer participation in network-and small-group-based virtual communities. International Journal of Research in Marketing, 21(3), 241–263.
Freeman, L. C., Roeder, D., & Mulholland, R. R. (1980). Centrality in social networks: II. Experimental results. Social Networks, 2(2), 119–141.
Furrer, O., Thomas, H., & Goussevskaia, A. (2008). The structure and evolution of the strategic management field: A content analysis of 26 years of strategic management research. International Journal of Management Reviews, 10(1), 1–23.
Garton, L., Haythornthwaite, C., & Wellman, B. (1997). Studying online social networks. Journal of Computer-Mediated Communication, 3(1), 1–32.
Godes, D. (2011). Commentary-invited comment on “opinion leadership and social contagion in new product diffusion”. Marketing Science, 30(2), 224–229.
Goel, S., & Goldstein, D. G. (2013). Predicting individual behavior with social networks. Marketing Science, 33(1), 82–93.
Green, P. E., & Tull, D. S. (1970). Research for marketing decisions. London: Prentice-Hall.
Gross, R., & Acquisti, A. (2005). Information revelation and privacy in online social networks. In Proceedings of the 2005 ACM workshop on Privacy in the electronic society (pp. 71–80). ACM
Hair, J. F., Sarstedt, M., Ringle, C. M., & Mena, J. A. (2012). An assessment of the use of partial least squares structural equation modeling in marketing research. Journal of the Academy of Marketing Science, 40(3), 414–433.
He, Q. (1999). Knowledge discovery through co-word analysis. Library Trends, 48(1), 133–159.
Hu, Y., & Van den Bulte, C. (2014). Nonmonotonic status effects in new product adoption. Marketing Science, 33(4), 509–533.
Hunter, D. R. (2007). Curved exponential family models for social networks. Social Networks, 29(2), 216–230.
Iacobucci, D., & Churchill, G. (2009). Marketing research: Methodological foundations. Boston: Cengage Learning.
Kostoff, R. N. (1993). Co-word analysis. Evaluating R&D impacts: Methods and practice (pp. 63–78). US: Springer.
Kozinets, R. V., De Valck, K., Wojnicki, A. C., & Wilner, S. J. (2010). Networked narratives: Understanding word-of-mouth marketing in online communities. Journal of Marketing, 74(2), 71–89.
Kratzer, J., & Lettl, C. (2009). Distinctive roles of lead users and opinion leaders in the social networks of schoolchildren. Journal of Consumer Research, 36(4), 646–659.
Lazzarini, S. G. (2007). The impact of membership in competing alliance constellations: Evidence on the operational performance of global airlines. Strategic Management Journal, 28(4), 345–367.
Leydesdorff, L. (2008). On the normalization and visualization of author co-citation data: Salton’s Cosine versus the Jaccard index. Journal of the American Society for Information Science and Technology, 59(1), 77–85.
Lin, M., Prabhala, N. R., & Viswanathan, S. (2013). Judging borrowers by the company they keep: Friendship networks and information asymmetry in online peer-to-peer lending. Management Science, 59(1), 17–35.
Liu, G. Y., Hu, J. M., & Wang, H. L. (2012). A co-word analysis of digital library field in China. Scientometrics, 91(1), 203–217.
Lowrey, T. M., Otnes, C. C., & Ruth, J. A. (2004). Social influences on dyadic giving over time: A taxonomy from the giver’s perspective. Journal of Consumer Research, 30(4), 547–558.
Muñoz-Leiva, F., Viedma-del-Jesús, M. I., Sánchez-Fernández, J., & López-Herrera, A. G. (2012). An application of co-word analysis and bibliometric maps for detecting the most highlighting themes in the consumer behaviour research from a longitudinal perspective. Quality & Quantity, 46(4), 1077–1095.
Newman, M. E., & Park, J. (2003). Why social networks are different from other types of networks. Physical Review E, 68(3), 036122.
Obstfeld, D. (2005). Social networks, the Tertius lungens and orientation involvement in innovation. Administrative Science Quarterly, 50(1), 100–130.
Park, S. H., & Luo, Y. D. (2001). Guanxi and organizational dynamics: Organizational networking in Chinese firms. Strategic Management Journal, 22(5), 455–477.
Pattison, P., & Robins, G. (2002). Neighborhood-based models for social networks. Sociological Methodology, 32(1), 301–337.
Robins, G., Snijders, T., Wang, P., Handcock, M., & Pattison, P. (2007). Recent developments in exponential random graph (p*) models for social networks. Social Networks, 29(2), 192–215.
Ronda-Pupo, G. A., & Guerras-Martin, L. Á. (2012). Dynamics of the evolution of the strategy concept 1962–2008: A co-word analysis. Strategic Management Journal, 33(2), 162–188.
Salton, G., & McGill, M. J. (1983). Introduction to modern information retrieval. New York: McGraw-Hill.
Wang, X., Cheng, Q., & Lu, W. (2014a). Analyzing evolution of research topics with NEViewer: A new method based on dynamic co-word networks. Scientometrics, 101(2), 1253–1271.
Wang, X. D., Liu, J. J., & Sheng, F. S. (2014b). Analysis of hotspots in the field of domestic knowledge discovery based on co-word analysis method. Cybernetics and Information Technologies, 14(5), 145–158.
Watts, D. J., & Dodds, P. S. (2007). Influential, networks, and public opinion formation. Journal of Consumer Research, 34(4), 441–458.
Wikipedia. (2014). (EB/OL) http://wikipedia.org/wiki/Social_network
Wu, C. C., & Leu, H. J. (2014). Examining the trends of technological development in hydrogen energy using patent co-word map analysis. International Journal of Hydrogen Energy, 39(33), 19262–19269.
Wuyts, S., Verhoef, P. C., & Prins, R. (2009). Partner selection in B2B information service markets. International Journal of Research in Marketing, 26(1), 41–51.
Yang, S., & Allenby, G. M. (2003). Modeling interdependent consumer preferences. Journal of Marketing Research, 40(3), 282–294.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Wang, Z., Zhao, H. & Wang, Y. Social networks in marketing research 2001–2014: a co-word analysis. Scientometrics 105, 65–82 (2015). https://doi.org/10.1007/s11192-015-1672-9
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11192-015-1672-9