text analytics

The Limitations of Transcripts: It is Time to Talk About the Elephant in the Room

Transcripts of qualitative in-depth interviews and focus group discussions (as well as ethnographers’ field notes and recordings) are typically an important component in the data analysis process. It elephant-in-the-roomis by way of these transcribed accounts of the researcher-participant exchange that analysts hope to re-live each research event and draw meaningful interpretations from the data. Because of the critical role transcripts often play in the analytical process, researchers routinely take steps to ensure the quality of their transcripts. One such step is the selection of a transcriptionist; specifically, employing a transcriptionist whose top priorities are accuracy and thoroughness as well as someone who is knowledgeable about the subject category, sensitive to how people speak in conversation, comfortable with cultural and regional variations in the language, etc.*

Transcripts take a prominent role, of course, in the utilization of any text analytic or computer-assisted qualitative data analysis software (CAQDAS) program. These software solutions revolve around “data as text,” with any number of built-in features to help sort, count, search, diagram, connect, quote, give context to, and collaborate on the data. Analysts are often instructed to begin the analysis process by absorbing the content of each transcript (by way of multiple readings) followed by a line-by-line inspection of the transcript for relevant code-worthy text. From there, the analyst can work with the codes taking advantage of the various program features.

An important yet rarely discussed impediment to deriving meaningful interpretations from Read Full Text

Words Versus Meanings

There is a significant hurdle that researchers face when considering the addition of qualitative methods to the-suntheir research designs.  This has to do with the analysis – making sense – of the qualitative data.  One could argue that there are certainly other hurdles that lie ahead, such as those related to a quality approach to data collection, but the greatest perceived obstacle seems to reside in how to efficiently analyze qualitative outcomes.  This means that researchers working in large organizations that hope to conduct many qualitative studies over the course of a year are looking for a relatively fast and inexpensive analysis solution compared to the traditionally more laborious thought-intensive efforts utilized by qualitative researchers.

Among these researchers, efficiency is defined in terms of speed and cost.  And for these reasons they gravitate to text analytic programs and models powered by underlying algorithms.  The core of modeling solutions – such as word2vec and topic modeling – rests on “training” text corpora to produce vectors or clusters of co-occurring words or topics.  There are any number of programs that support these types of analytics, including those that incorporate data visualization functions that enable the researcher to see how words or topics congregate (or not), producing images such as these Read Full Text