applying text mining & analytics to consumer satisfaction surveys - case study
DESCRIPTION
Collective Intellect (CI) worked with a leading Fortune 500 hospitality company to analyze their customer satisfaction surveys. Our client understood a portion of their customers were unhappy with their hotel rooms; they just didn’t know why.TRANSCRIPT
2040 14th Suite 200 Boulder, CO 80302 720-259-3060 http://www.collectiveintellect.com
Our Client’s Goals Collective Intellect (CI) worked with a leading Fortune 500 hospitality company to analyze their customer satisfaction surveys. Our client understood a portion of their customers were unhappy with their hotel rooms; they just didn’t know why. Existing client research methodologies and analytic systems had failed to uncover the reasons customers were dissatisfied, so CI was tasked with surfacing more precise causation for customer complaints. Results Applying sophisticated language modeling, CI was able to isolate negative guest sentiment to
specific areas in the hotel room and property. Collective Intellect utilizes Latent Semantic Analysis (LSA) and Natural Language Processing (NLP) to deliver highly accurate analysis and associated observations from unstructured data. Whether it’s social, email, chat transcripts or surveys, and if data is text then CI possesses the capability to run analysis.
Project Highlights
Goal – Analyze customer surveys to better understand consumer dissatisfaction with hotel room features.
Results – Our semantic and text analytics technology was able surface precise insights into why customers did not enjoy staying in their hotel room.
2040 14th Suite 200 Boulder, CO 80302 720-259-3060 http://www.collectiveintellect.com
How CI Approached the Project
Working with our client, CI first determined the status of their existing analytics effort. Together, we concluded that CI’s unique approach to how data is handled, categorized and measured for relevancy could uncover additional insights their existing systems and methodologies were unable to
surface.
Using CI’ robust categorization engine, we were able to isolate specific attributes from consumer responses related to dissatisfaction with their hotel rooms and other features of the property such as the spa and onsite restaurants. Thereafter, we were then able to identify and dissect specific root causes for dissatisfaction such as cost, convenience, and comfort.
Suggested Next Steps CI recommended that its hospitality client automate their analysis of customer
surveys in an “always on” dashboard for real-‐time tracking. This approach would ensure that consumer reaction to changes could be monitored and tracked. We also recommended that the resulting information be integrated into an existing CRM system, including mapping surveys results to any social media profiles.
The CI Semantic Methodology CI utilizes semantic technology based on Latent Semantic Analysis (LSA) to expose latent contextual-‐meaning within a large body of text. Sophisticated language processing is the critical foundation for successful analysis. Accurate insights from text analytics that are repeatable, scalable and consistent can
2040 14th Suite 200 Boulder, CO 80302 720-259-3060 http://www.collectiveintellect.com
only be achieved using technology that is able to categorize enormous volumes of structured and unstructured data via dimension such as consideration and preference, intent, demographics and sentiment, just to name a few.
CI Services & Tools Used on Project CI:Insight - multi-‐dimensional analysis, blended qualitative and quantitative analysis, demographics and psychographics analysis, in an integrated consumer conversation analytical hub intended for Power Analyst functions and accessed via SaaS model.