Making Words Speak: Leveraging Consumer Insights from Online Review Text to Improve Service Quality

Andrea Ordanini, Raji Srinivasan, and Anastasia Nanni, 2018, 18-119-07

View Slides

How do managers make sense of online reviews? Although numeric online ratings provide summary consumer feedback, they are not highly diagnostic (e.g., there is often a j-shaped distribution). Review text, which includes details of consumers’ experiences, may offer deeper insights but such text is unstructured, with contextually-driven meanings, and thus is challenging to exploit.

In this report, Andrea Ordanini, Raji Srinivasan, and Anastasia Nanni examine whether managers can leverage consumer insights from text mining analysis of online review text to improve their firm’s performance. 

They examine whether managerial use of online review text analytics, derived from extraction and visual representation of insights in review text, affects the service quality of their firm’s offering. They focus on service quality as online consumer reviews are critical in consumers’ purchase decisions in many service sectors (e.g., hotels, airlines, restaurants, and retailing).

They also examine the heterogeneous effects of managers’ use of online review text analytics on service quality based on two contextual characteristics of the managers’ environment: managerial accountability and prior firm performance.

They use a longitudinal randomized control trial (RCT) in a field setting in 135 Italian hotels to provide causal evidence for effects. They conducted the RCT over a period of eight months, using monthly average online ratings from TripAdvisor for June-August 2015 and June-August 2016 as measures of pre- and post-treatment service quality of the hotel respectively.

Results indicate that the managerial use of online review text analytics improved service quality by 5.4% during the treatment window. The effect size was not trivial and was robust to several alternative assumptions. Additional analysis indicated that managers who used online review text analytics were more likely to identify points of weakness in their offering and take actions to address those.

Importantly, the positive effect of review text analytics disappears when managers do not feel accountable for their actions or when managers are satisfied with the existing level of performance. Thus, decisional stimuli and organizational characteristics are important boundary conditions for the positive effect.

Andrea Ordanini is BNP Paribas Professor of Marketing and Service Analytics, Bocconi University. Raji Srinivasan is Sam Barshop Centennial Professor of Marketing Administration, Red McCombs School of Business, University of Texas at Austin. Anastasia Nanni is a doctoral student in Marketing, Bocconi University.

Related links

Large-Scale Cross-Category Analysis of Consumer Review Content on Sales Conversion Leveraging Deep Learning
Xiao Liu, Dokyun Lee, and Kannan Srinivasan (2018) [Report]


  • Corporate: FREE
  • Academic: FREE
  • Subscribers: FREE
  • Public: $18.00



Employees of MSI Member Companies enjoy the benefits of complete online access to content, member conferences and networking with the MSI community.



Qualified academics benefit from a relationship with MSI through access to, conferences and research opportunities.



The public is invited to enjoy partial access to content, a free e-newsletter, selected reports and more.




Learn more about becoming a member of the institute

Read More

Stay Informed

The MSI Mailing List

Subscribe to our email list to stay informed about upcoming events, news, etc.

Social Media