•SEM and bootstrapping cluster analysis offer different types of insights.•Simulated SEM and bootstrapping cluster simulations are both useful in validating scales.•Bootstrapping cluster simulations ...aid in validating constructs in smaller, moderately correlated data sets.•Bootstrapping cluster simulations validate scales visually with probability estimates.
The scale development paradigm was created to improve the measurement of latent constructs. Although several statistical techniques have been successfully integrated into the overall process, identifying factor patterns and validating constructs using smaller datasets with different correlational structures remain a concern. This paper presents heatmapping and bootstrapping cluster analysis (HMBCA), a novel machine-learning based diagnostic workflow, as a new tool to aid in strengthening the process. A substantive example on the overall organizational knowledge acquisition behaviors demonstrates that the bootstrapping cluster simulation approach provided promising results regarding the factor structure as measured by the Approximately Unbiased (AU) p-values under the following conditions: when factor correlations are weaker or moderate, with simulated data containing smaller samples. The study suggests that researchers may leverage bootstrapping cluster simulations to validate constructs through both visual inspection and probability estimates when faced with constraints such as a small sample size.
Purpose
To unlock social media’s value, this study aims to integrate insights from several theoretical perspectives and the relevant literature, developing an extended social media analytics ...framework. It identifies the stages underlying the social media analytics process and tests the framework in three important and interconnected areas: social media (Twitter), new product adoption (iWatch and Google Glass) and social media analytic techniques (text mining and sentiment analysis).
Design/methodology/approach
Based upon a systematic review of different research approaches, theories and media types, this paper presents and tests an extended framework in three important and interconnected areas mentioned above.
Findings
This paper offers a theory-driven social media analytics framework. It validates the framework by providing concrete processes, examples, evidence and insights related to three chosen areas mentioned above, thereby helping managers create effective and efficient social media and new product development strategies.
Originality/value
This paper integrates insights from theories of the middle range (Merton, 1949), Campbell’s (1965) model of sociocultural evolution and Fan and Gordon’s (2014) social media analytics framework, developing its own extended social media analytics framework and validating it in three important and interconnected areas mentioned above. This paper demonstrates not only how the proposed framework can be applied to the context of new product development, but also how social media are transforming research approaches (qualitative, quantitative and mixed method) and the very nature of business itself (increased importance of digital business).
USER-GENERATED CONTENT AS WORD-OF-MOUTH Ramirez, Edward; Gau, Roland; Hadjimarcou, John ...
Journal of marketing theory and practice,
04/2018, Letnik:
26, Številka:
1-2
Journal Article
Recenzirano
The objective of this research is to identify two harvestable word-of-mouth (WOM) proxies and test their construct validity. Bivariate measures of association of user-generated content (UGC) data ...compiled from Facebook.com on sixty-one firms across nine markets suggest the WOM proxies were positively correlated, maintaining varying relationships with firms' stock market performance. Study two uses time-series analysis to demonstrate that these WOM proxies change in tandem with stock prices, implying that they are sensitive to firm behaviors and that UGC is a leading indicator of stock market performance. As such, the findings provide managers with a tool to more accurately assess impressions of the firm.
Purpose
To unlock social media’s value, this study aims to integrate insights from several theoretical perspectives and the relevant literature, developing an extended social media analytics ...framework. It identifies the stages underlying the social media analytics process and tests the framework in three important and interconnected areas: social media (Twitter), new product adoption (iWatch and Google Glass) and social media analytic techniques (text mining and sentiment analysis).
Design/methodology/approach
Based upon a systematic review of different research approaches, theories and media types, this paper presents and tests an extended framework in three important and interconnected areas mentioned above.
Findings
This paper offers a theory-driven social media analytics framework. It validates the framework by providing concrete processes, examples, evidence and insights related to three chosen areas mentioned above, thereby helping managers create effective and efficient social media and new product development strategies.
Originality/value
This paper integrates insights from theories of the middle range (Merton, 1949), Campbell’s (1965) model of sociocultural evolution and Fan and Gordon’s (2014) social media analytics framework, developing its own extended social media analytics framework and validating it in three important and interconnected areas mentioned above. This paper demonstrates not only how the proposed framework can be applied to the context of new product development, but also how social media are transforming research approaches (qualitative, quantitative and mixed method) and the very nature of business itself (increased importance of digital business).
One of the most important determinants of performance for any firm is the unique bundle of resources the company possesses. To date, however, empirical results on whether “familiness” as an element ...of this resource bundle has a positive or negative impact on firm performance have been mixed (Dyer, 2018; Gottardo & Moisello, 2019; Oswald
et al.
, 2009; Pitchayado
et al.
, 2018). This paper employs structural equation modeling to examine how entrepreneurs in China’s Zhejiang Province include members of their nuclear families, extended kin networks, and professional networks in their top management teams to access different bundles of family and non-family human resources, leading to variance in firm performance results. We find firms that leverage “guanxi” (a particular concept of kin, common in China but not often employed as a construct in western-based research, which encompasses both extended family members and close friends) for industry, technical, or entrepreneurial expertise enjoy certain types of higher performance results. In comparison, firms that leverage nuclear family members for management or marketing expertise achieve certain types of lower performance results. Post-hoc analysis indicates that leveraging guanxi specifically for prior entrepreneurial experience or for technical expertise leads to greater employee growth and higher subjective assessment of success. Conversely, leveraging nuclear family members for management or technical expertise leads to lower levels of these same performance variables. However, only firm size, measured by number of employees at venture founding, is predictive of revenue growth.
In recent years, companies have become aggressive in investing in Big Data Analytics (BDA) for marketing purposes, particularly new product development. One of the basic features of BDA is its ...promise in delivering automated recommendations or knowledge. For this reason, companies attempt to ascertain if BDA can improve new product performance beyond what Traditional Marketing Analytics (TMA) can. The overarching question is whether different combinations (BDA and TMA in different levels) of analytics capabilities are able to generate different kinds of knowledge for Knowledge and Information Fusion that could improve new product performance. The aim of this study is to build and assess the Knowledge Fusion Taxonomy, and then determine the attributes that are most critical in affecting knowledge generation, Knowledge and Information Fusion, and new product development. Multiple correspondence analysis (MCA), Fuzzy Set QCA, Partial least squares path modeling (PLS-PM), and SEM are the main statistical approaches used in this study to test the model. Heatmaps were also generated to allow users to easily explore trends or dimension patterns of items and latent variables. In general, the study suggests that BDA is an important complementary capability instead of a competing capability with TMA. The results identified by the MCA, Fuzzy Set QCA, and PLS-PM may provide such a roadmap for firms to improve key capabilities in analytics, knowledge discovery and integration, and new product development. The study supports the hypothesized effects of competing analytics capabilities (TMA and BDA) on knowledge generation, and also a positive effect of knowledge generation and Knowledge and Information Fusion on new product performance. In particular, both the Knowledge Fusion Taxonomy and the PLS-PM suggest that when combining information and knowledge in a complex manner, Automated Knowledge is more important than other types of knowledge. Therefore, to capture the pioneer position as shown in the Knowledge Fusion Taxonomy, companies need to build new capabilities on Automated Knowledge generation by synthesizing the unique combination of analytics capabilities. In addition, Heuristic Knowledge was also found to be a moderator when firms adopt high levels of BDA to generate Automated Knowledge. This paper establishes a solid conceptual and data analysis framework for analytics and knowledge capabilities (i.e., discovery and fusion) on new product performance. Additionally, the study provides managers a roadmap to focus on important issues in analytics and knowledge discovery for improving new product performance.
In the enterprise marketing process, on-line data plays more and more important role. As a type of data, spam (or fake) reviews of the products, however, have been seriously affecting the reliability ...of both decision making and data analysis of the enterprise. To detect spam reviews, the paper presents a set of opinion spam detection's identification indicators based on behavior features of the spammer. Two algorithms are then proposed to recognize similar reviews and relevant reviews from all reviews. Compared to the traditional algorithm, our review identification algorithm achieves shorter execution time. More importantly, the proposed algorithm for recognizing relevant reviews can be used to analyze the relevancy between the review content and the given review topic by using the automatic word segmentation technique. The Experimental results show that the number of fake reviews by our algorithms is higher than that of the traditional algorithm. Moreover, we found that about 46% of the mobile phone reviews on the Amazon website were irrelevant to the product's topic, and 54.7% of the reviews were similar to other reviews.
In the paper, we propose a method to automatically generate test cases for the program with nested loops. Our approach first constructs the layer model of the program by scanning procedure source ...code. Then, through the method of model refinement, the layer model is converted to the extended regular expression model. Next, we can get a set of test paths from the extended regular expression model according to algebraic operations and constraint conditions in the program. Finally, test cases of the program are constructed by using logical operations for these test paths. Compared with those traditional graph-based test case generation methods, our method can produce a set of executable test cases to satisfy a given test coverage criterion without having to build the control flow diagram of the program in unit testing. In addition, our method can also effectively avoid the state space explosion problem.
Software testing has become an essential activity to guarantee software quality. To reduce the overall cost of software testing, model-based testing has been widely studied in the past two decades ...and Finite State Machine (FSM) is used to build the model of software behaviors. However, due to the inadequacy of the modeling ability of FSM, FSM-based testing cannot be taken as a test oracle to solve all issues in software testing. To improve the modeling capability of the model, a few researchers have proposed using Extended Regular Expressions (ERE) to model software behaviors. This paper reviews the method of the ERE-based testing and presents six modeling rules to convert program codes to the ERE model. Then, a case is adopted to illustrate the process of generating executable paths from the ERE model and the method of designing test cases by those paths. Compared with the traditional graphic traversal method of constructing executable paths from the program, ERE not only has robust modeling capability to describe more types of software behaviors than FSM, but also can be used to construct effective executable paths to detect program errors.
The paper presents a test suite reduction approach based on probability models in regression testing. First, we model the process of software testing by using the joint probability of both test cases ...and program faults, and propose two probability models for the software's old and new versions, respectively. Then, a theorem combining set operations and probability models is given to implement our approach. Different from the traditional coverage-based test suite reduction methods, the reduced test suite constructed by our approach does not need to cover all test requirements, but also remains the same fault detection capability of the original test suite.The paper presents a test suite reduction approach based on probability models in regression testing. First, we model the process of software testing by using the joint probability of both test cases and program faults, and propose two probability models for the software's old and new versions, respectively. Then, a theorem combining set operations and probability models is given to implement our approach. Different from the traditional coverage-based test suite reduction methods, the reduced test suite constructed by our approach does not need to cover all test requirements, but also remains the same fault detection capability of the original test suite.