The text mining revolution
18 July 2011
The analysis of textual information from surveys, online sources and client databases is a hot topic for research professionals.
Forms of text mining and analysis tools have been used in mainstream customer, brand, employee and social research, for some time. These have included solutions such as first and second generation natural language processing (NLP) software as well as various coding tools.
A more advanced offering
Over the last six years, ORC International has been integrating a number of text mining advances into its standard and bespoke studies. The solutions that are now offered to clients are representative of a company that is driven to deliver innovation through cutting-edge technology.
Our text mining capabilities can help clients in a wide range of areas. It can be used to help with the analysis of verbatim responses collected via questionnaires (CATI/online). Text mining can also assist with the examination of transcript, forums and reports from a qualitative research exercise, and the analysis of feedback received from consultation studies.
The software can be used in both large and small studies, but is most powerful when integrated into studies with high response rates and regular tracking projects. On these larger projects, the ability to automate tasks like cleaning, categorisation and analysis, can be very useful. As well as making the process smoother, it can drive costs down and improve turnaround times after the initial set-up and calibration phase.
Not a black box approach
The team at ORC International work closely with every client to devise questionnaires and create a reporting taxonomy that will maximise the insight that can be retrieved from the final data. The data mining tool enables our analysts and statisticians to dissect the individual responses, analyse keywords, phrases, themes and sub-themes.
The approach has allowed us to help clients understand research in ways that would not have been possible with quantitative data alone. Recent projects have allowed us to help clients:
- Determine the key emotional and behavioural drivers behind customers’ perceptions of value for money and likelihood to recommend
- Develop detailed pen-portraits behind key customer groups, their attitudes and behaviours
- Delve deep into comments received about customer service complaints. This helps to uncover the key staff traits that can impact on the effectiveness of problem resolution
Tomorrow’s world
As we have developed our current offering, we have had to tackle many issues with management and processing, as well as the analysis and reporting of textual research data. Technology continues to evolve and over the next year we are striving to make continued improvements to areas including sentiment extraction and analysis, the accuracy of NLP comprehension and multiple language processing.
