Comparing consumer-produced product reviews across multiple websites with sentiment classification

ABSTRACT

Online consumer reviews have been extensively studied. However, existing literature analyzing online consumer review data mostly relies on a single data source, resulting in potentially biased analytics conclusions. Many websites encourage consumers to post reviews of their purchased products, so that new consumers can evaluate these reviews for the same product across different websites to help them make purchasing decisions. Confusions often arise in this process, because there often exist substantial discrepancies in customer reviews across different retailers on the same product. Clarifying such confusions can help consumers reduce concerns to make up their mind for their purchases, therefore benefiting both consumers and retailers. Through text analytics and sentiment analysis, we comparatively examine the underlying patterns of online consumer reviews of three large retailers including Sears, Home Depot, and Best Buy for a same product. Afterward, we combine online consumer reviews from these large retailers and conduct an overall text analytics and sentiment analysis. The overall results are further compared with the results from individual retailers. The findings show that the sentiment of the online consumer reviews could vary substantially so relying on a single data source to make purchase decision is not a wise idea. Based on the results, we further devise a framework to comparatively examine and integrate multiple data sources for social media analytics of online consumer reviews. This study offers important managerial implications and identifies several new research directions for social media analytics.     

Macroeconomy and the well-being of low income African American families

By employing unit root testing and cointegration procedures, this paper is the first study of its kind to present empirical evidence showing higher inflation rate, lower unemployment, and increased real per capita gross domestic product decreased the poverty rate among African American families during the 1966–99 period. The findings, estimated using the Phillips-Hansen fully modified OLS estimator, are also consistent with results obtained using Johansen’s maximum likelihood cointegration procedure. Long-run Granger causality, inferred by the estimated error-correction model, suggests that the African American poverty rate is not weakly exogenous and will respond to policy intervention.     

The Feldstein–Horioka puzzle in Latin American and Caribbean countries: a panel cointegration analysis

In this paper, the recently developed panel unit root and the Pedroni cointegration tests are applied to empirically examine the validity of the Feldstein–Horioka puzzle (F–H puzzle) for a heterogeneous panel of 14 Latin American and five Caribbean countries over the period, 1960–2002. The findings indicate that in these countries, the long-run solvency condition is maintained. Finally, employing the Pedroni panel group FM-OLS estimator (2000, 2001), it is found that the statistically significant estimated savings-retention coefficient for the panel is relatively small indicating that the F–H Puzzle is not valid and thus implying the prevalence of a moderate degree of capital mobility.

Relational configurations with information intermediaries: The effect of firm‐investment bank ties on expected acquisition performance

Recognizing information‐related problems in acquisition transactions, we study how the characteristics of acquiring firms' relationships with information brokers or intermediaries like investment banks affect firms' access to acquisition‐related information, thus influencing expected acquisition performance. We propose that relational configurations that enhance the intermediaries' ability and willingness provide the most beneficial and appropriate information to acquiring firms. We find that acquirers' expected acquisition performance increases with the number of prior transactions with investment banks but decreases when relationships with banks become exclusive. Further, the positive effect of number of prior transactions becomes even stronger for less related acquisitions. Our study provides insights on the beneficial performance implications of competition in multiple but nonexclusive relationships with information intermediaries such as investment banks. Copyright © 2013 John Wiley & Sons, Ltd.     

A Time-Series Investigation of the U.S. Real Health Expenditure: Evidence from Nonlinear Unit Root Tests

This paper contributes to the literature on health expenditure studies by applying the non-linear unit root tests formulated recently by Kapetanios et al. (Journal of Econometrics 112(2):359?C79, 2003) to empirically test whether the U.S. real health expenditure time-series are non-stationary or non-linear and globally stationary during a relatively long period from 1965 to 2009. For comparison purposes, it also reports the results of a battery of traditional linear unit root tests and the Lee and Strazicich??s minimum LM unit root (Review of Economics and Statistics 85(4):1082?C1089, 2003) test for structural breaks. The empirical findings of the paper show that in the United States during the period under investigation, the real health expenditure time-series are non-stationary in levels. Policy implications of the empirical findings are discussed.     

Aggregate health care expenditure in the United States: evidence from cointegration tests

Unlike recent studies that are based on international cross-sectional series, this paper attempts to quantify the role of the determinants of aggregate health care expenditure per capita, using time-series data for the period of 1960–87 for the United States. The paper applies the relatively new procedures of unit root testing, cointegration and error-correction modelling. The evidence supports cointegration. Although, the results indicate that per capita income, age of the population, number of practising physicians, and public financing of health care are important determinants, the age structure of the population and number of practising physicians emerge as the major determinants of aggregate health care expenditure in the United States.     

The relationship between budget deficits and capital inflows: Further econometric evidence

This research note examines the impact of federal deficits on U.S. capital inflows. Expanding on the previous work of Bahmani-Oskooee and Payesteh (1994), we employ the relatively new maximum likelihood procedure developed byJohansen (1988) andjohansen andJuselius (1990) to do cointegration tests. The results find a long run relationship between budget deficits and capital inflows. In addition, findings from error-correlation modeling reveal that short-run disequilibria in financial markets are corrected very rapidly, suggesting that these markets are efficient.