Creating social intelligence for product portfolio design

Li, Yung-Ming; Chen, Hsuan-Ming; Liou, Jyh-Hwa; Lin, Lien-Fa

doi:10.1016/j.dss.2014.06.013

Cited by 52 publications

(24 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We argue that social media facilitate firms’ information flow and knowledge sharing across internal and external social networks, which enhance internal and external collaboration, and allow firms to be more customer‐oriented, contributing to operational efficiency and innovativeness improvement. By strategically enhancing information flow and knowledge acquisition, firms are likely to improve their capability in new product/service development and idea generation, leading to enhancement in both efficiency and creativity (Li et al., 2014). To test our hypotheses, we collected longitudinal performance data from 2006 to 2012 and examined firms’ social media initiatives in 281 organizations between 2006 and 2011 (Section 3 provides the details).…”

Section: Introductionmentioning

confidence: 99%

The impact of firms’ social media initiatives on operational efficiency and innovativeness

Lam

Yeung

Cheng

2016

J of Ops Management

175

166

View full text Add to dashboard Cite

Social media have been increasingly adopted for organizational purposes but their operational implications are not well understood. Firms' social media initiatives might facilitate information flow and knowledge sharing within and across organizations, strengthening firm-customer interaction, and improving internal and external collaboration. In this research we empirically examine the impact of social media initiatives on firms' operational efficiency and innovativeness. Taking the resource-based view of firms' information capability, we consider firms' social media initiatives as strategic resources for operational improvement. We posit that firms' social media initiatives enhance dynamic knowledgesharing routines through an information-rich social network, leading to both operational efficiency and innovativeness. Collecting secondary data in a longitudinal setting from multiple sources, we construct dynamic panel data (DPD) models. Based on system generalized method of moments (GMM) estimation, we show that firms' social media initiatives improve operational efficiency and innovativeness. We identify the importance of an information-rich social network to the creation of knowledge-based advantage through firms' social media initiatives, and discuss the theoretical and managerial implications from the perspective of operations management.

show abstract

Section: Introductionmentioning

confidence: 99%

The impact of firms’ social media initiatives on operational efficiency and innovativeness

Lam

Yeung

Cheng

2016

J of Ops Management

175

166

View full text Add to dashboard Cite

show abstract

“…Lee & Bradlow (2007) emphasize the importance of online product reviews for conjoint analyses in marketing and propose a text mining technique to extract the product features discussed in online product reviews, as well as consumers' sentiment orientations toward these features. Li et al (2014) develop a social intelligence mechanism to extract and consolidate the reviews expressed via social media and to derive insights to help firms make decisions on product portfolio design. Decker and Trusov (2010) propose three econometric models (i.e., Poisson regression, negative binominal regression, and latent class Poisson regression models) to measure aggregate consumer preferences from online product reviews about mobile phones.…”

Section: Existing Preference Measurement Methodsmentioning

confidence: 99%

“…Second, online product reviews are voluntarily produced by actual consumers (Decker & Trusov, 2010;Netzer et al, 2008) and do not depend on surveys or respondents. Prior studies have shown that consumer opinions expressed in online product reviews offer a good proxy for the overall WOM of the products being discussed and then become a new source of preference data (Archak et al, 2011;Decker & Trusov, 2010;Zhu & Zhang, 2010;Li et al, 2014). Thus, online product reviews represent a more representative preference dataset than those collected by surveys or experiments.…”

Section: Introductionmentioning

confidence: 96%

Crowd intelligence: Analyzing online product reviews for preference measurement

Xiao

Wei

Dong

2016

Information & Management

111

View full text Add to dashboard Cite

“…These online texts are valuable for the improvement of government, company and consumer decision making. Governments can make sounder public decisions by analyzing their citizens' online texts on social issues [3], companies can identify product weaknesses and forecast market demand by analyzing online product reviews [6,22,25] and consumers can make suitable purchasing decisions by identifying the sentiment orientation of a large number of online product reviews [18,46]. Several studies on opinion mining and sentiment analysis have been conducted to automatically mine the opinions embedded in the vast repository of online texts and analyze the sentiment classes of a massive number of online texts.…”

Section: Introductionmentioning

confidence: 99%

A method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm

Liu

Fan

2017

Information Sciences

170

View full text Add to dashboard Cite

Multi-class sentiment classification is a valuable research topic with extensive applications; however, studies in the field remain relatively scarce. In the present paper, a method for multiclass sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm is proposed. First, an improved OVO strategy is proposed wherein the relative competence weight of each binary classifier is determined according to the K nearest neighbors and the class center of each class in the training sample set concerning the binary classifier. A method for multi-class sentiment classification is proposed based on this improved OVO strategy and the SVM algorithm. After converting the training texts into term feature vectors, the important features (terms) for multi-class sentiment classification are selected using the information gain (IG) algorithm. A binary SVM classifier is then trained on the training feature vectors of each pair of sentiment classes. To identify the sentiment class of a test text, a confidence score matrix of multiple SVM classifiers is constructed based on the results of multiple SVM classifiers. Using this score matrix, the sentiment class of the test text can be determined using the improved OVO strategy. The results of our experimental studies show that the performance of the proposed method is significantly better than that of the existing methods for multi-class sentiment classification.

show abstract

Creating social intelligence for product portfolio design

Cited by 52 publications

References 20 publications

The impact of firms’ social media initiatives on operational efficiency and innovativeness

The impact of firms’ social media initiatives on operational efficiency and innovativeness

Crowd intelligence: Analyzing online product reviews for preference measurement

A method for multi-class sentiment classification based on an improved one-vs-one (OVO) strategy and the support vector machine (SVM) algorithm

Contact Info

Product

Resources

About