This ambitious project involves the development of a powerful tool for the automatic analysis of 100% of the comments of our quantitative surveys always with client centricity in mind. Through text mining models, a machine learning technique applied to non-structured data, we have managed to classify instantaneously the type of comment, the subject and the sentiment. In this way, it is possible to prioritize the most critical items, identify points for improvement and analyze the feasibility of the suggestions offered by our customers.
In 2012, ESOMAR published 24 Questions to Help Buyers of Social Media Research. These questions were intended to help users of social media research consider issues that might influence whether a social media listening tool was fit for the purpose of a particular research objective, whether qualitative, quantitative, or both. The questions were designed to help users gain a better understanding of the services being offered and ensure that what they received from a social media data provider was what was expected. Over the intervening years a great deal has changed in terms of the types of data available for analysis, the sources for such data, the ways in which researchers acquire and analyze it, the technologies used, the industry players, and the regulatory environment, to name a few. Of special note is the interest in moving beyond text to include the broader category of unstructured data (text, images, audio, and video) and the expansion of potential sources beyond social media to include, for example, survey open ends, focus group transcripts, call center interactions, and more. At the same time, the software tools for analyzing these types of data have grown in number and capabilities. The purpose of this document is to update ESOMAR's guidance to better reflect current practice in market, opinion, and social research and data analytics.