Mining consumer dialog in online forums

Kaiser, Carolin; Bodendorf, Freimut

doi:10.1108/10662241211235653

Cited by 43 publications

(40 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Objective statements are fact based, including information, questions, and replies/answers, which have frequently been employed in the analysis of tweets (de Maertelaere et al, 2012;Kwon and Sung, 2011). Subjective statements are judgmental in nature, such as criticism or praise; in other words, positive or negative opinions (Kaiser and Bodendorf, 2012 message is expected to be shared and circulated in public (Shu and Chuang, 2011), thus serving as a driver of social capital (Shanahan and Hopkins, 2007). We believe that the presence of knowledge sharing serves as an indicator of prosumers.…”

Section: Customer Engagement In Social Mediamentioning

confidence: 99%

Using Twitter to engage with customers: a data mining approach

et al. 2015

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to explore customer engagement in Twitter via data mining. Design/methodology/approach -This study's intended contributions are twofold: to find a clear connection among customer engagement, presumption, and Web 2.0 in a context of service-dominant (S-D) logic; and to identify social networks created by prosumers. To this end, the study employed data mining techniques. Tweets about IKEA were used as a sample. The resulting algorithm based on 300 tweets was applied to 4,000 tweets to identify the patterns of electronic word-of-mouth (eWOM). Findings -Social networks created in IKEA's tweets consist of three forms of eWOM: objective statements, subjective statements, and knowledge sharing. Most objective statements are disseminated from satisfied or neutral customers, while subjective statements are disseminated from dissatisfied or neutral customers. Satisfied customers mainly carry out knowledge sharing, which seems to reflect presumption behavior. Research limitations/implications -This study provides partial evidence of customer engagement and presumption in IKEA's tweets. The results indicate that there are three forms of eWOM in the networks: objective statements, subjective statements, and knowledge sharing. It seems that IKEA successfully engaged customers in knowledge sharing, while negative opinions were mainly disseminated in a limited circle. Practical implications -Firms should make more of an effort to identify prosumers via data mining, since these networks are hidden behind "self-proclaimed" followers. Prosumers differ from opinion leaders, since they actively participate in product development. Thus, firms should seek prosumers in order to more closely fit their products to consumer needs. As a practical strategy, firms could employ celebrities for promotional purposes and use them as a platform to convert their followers to prosumers. In addition, firms are encouraged to make public how they resolve problematic customer complaints so that customers can feel they are a part of firms' service development. Originality/value -Theoretically, the study makes unique contributions by offering a synergic framework of S-D logic and Web 2.0. The conceptual framework collectively relates customer engagement, presumption, and Web 2.0 to social networks. In addition, the idea of examining social networks based on different forms of eWOM has seldom been touched in the literature. Methodologically, the study employed seven algorithms to choose the most robust model, which was later applied to 4,000 tweets.

show abstract

Section: Customer Engagement In Social Mediamentioning

confidence: 99%

Using Twitter to engage with customers: a data mining approach

et al. 2015

View full text Add to dashboard Cite

show abstract

“…To glean useful information from a large number of textual documents quickly, it has become imperative to use automated computer techniques Chiang et al, 2011;He, 2013a). Text mining is focussed on finding useful models, trends, patterns or rules from unstructured textual data (Hung and Zhang, 2008;Romero et al, 2008;Lin et al, 2009;Abdous and He, 2011;Kaiser and Bodendorf, 2012). Different from traditional content analysis, the main purpose of text mining is to automatically identify useful patterns or trends hidden in the text documents (He, 2013b;Zhong et al, 2012).…”

Section: A Brief Review Of Text Miningmentioning

confidence: 99%

“…. Second, to further increase our coverage for social media mashups, we also examined the messages posted in the online forum (Kaiser and Bodendorf, 2012) of the largest web mashup repository web site programmableweb. As of December 20, 2012, there were 2,392 messages available in the online forum of Social media mashups programmableweb.…”

Section: Intr 242mentioning

confidence: 99%

Insights into the adoption of social media mashups

Zha

2014

Internet Research

View full text Add to dashboard Cite

Purpose -The existing mashup literature paid little attention to the actual adoption and diffusion of mashups in an organizational context. As more and more organizations are engaged in mashup initiatives, more research efforts focussing on the mashup use and adoption issues from the organizational perspective are needed to ensure that organizations can receive the maximum benefits from their mashup initiatives. Two studies are conducted to increase the understanding of the use and adoption issues with social media mashups. The paper aims at discussing these issues. Design/methodology/approach -The paper first used a text mining approach to analyze relevant posts on blogs and messages in a major online mashup forum in order to understand the current status of social media mashup as well as representative themes and issues with social media mashups in general. Subsequently, the paper reviewed a number of social media mashup sites created by higher education institutions (HEIs) in the USA. Findings -The paper identified some representative themes and issues with social media mashups in general. The paper also identified the approaches that were used to design the interface of social media mashup sites by HEIs. Based on the two studies, this paper provides recommendations and insights to guide social media mashup development and adoption in an organizational context. Originality value -This is the first article to discuss the use and adoption of social media mashups in organizational environments. This paper can be used as a starting point to motivate other researchers to further explore the diffusion of social media mashups in different industries. This paper also helps organizations improve their social media mashup initiatives.

show abstract

“…Online discussion allows people to interact with other people in web (Schellens and Valcke, 2005;Wright and Street, 2007;Kaiser and Bodendorf, 2012). An online discussion is not fixed in time or space: participants can log on at any time from any internet-enabled computer to seek clarification for issues they encounter in their interest, to discuss topics raised in web, or to initiate new discussions on related topics (DeSanctisa et al, 2003;Chung and Han, 2013).…”

Section: Introductionmentioning

confidence: 99%

Solving strategy for unintended criticism in online space

Chung

2015

Internet Research

View full text Add to dashboard Cite

Purpose -The purpose of this paper is to examine how information load, consumers' regulatory focus, and prior attitudes interact to influence consumers' response to firm crisis in the context of online discussion forum. By doing this, this study presents the solving strategy for unintended criticism in online space. Design/methodology/approach -Based on selective exposure and regulatory focus theory, the author proposes that consumers' regulatory focus and prior attitudes toward a focal firm influence the relationship between information load and selective exposure phenomenon. The data for this study are obtained from an experimental research design. Data were collected from 165 college students who have an experience with an online discussion forum. Findings -The author finds that selective exposure is likely to occur when information load is high (vs low). More importantly, this selective exposure is influenced by regulatory focus. Preventionfocussed consumers with favorable (vs unfavorable) prior attitudes toward the target firm tend to evaluate it less favorably, whereas promotion-focussed consumers with unfavorable (vs favorable) prior attitudes are likely to evaluate it more favorably when information load is high. Originality/value -Evidence is found that consumers' regulatory focus moderates the effect of information quantity on confirmatory information search, and induces different response strategies to firm crisis information.

show abstract

Mining consumer dialog in online forums

Cited by 43 publications

References 57 publications

Using Twitter to engage with customers: a data mining approach

Using Twitter to engage with customers: a data mining approach

Insights into the adoption of social media mashups

Solving strategy for unintended criticism in online space

Contact Info

Product

Resources

About