Amongst all the tech-related terms that we hear today, some of them are less popular than others, but that doesn’t mean that they are less important. A good example is Content Analysis or Document Analysis.
The goal of content analysis (document analytics) is to make a qualitative analysis of documents that can be digital, but also physical. The very first step of the analysis process aims to code the content of the documents into categories. After the classification is completed the analysis may start, and it usually includes texts, but also videos or photos. A good example of classified document analysis is the review of the answers of an NPS survey. Another one is the study of a business contract, divided into all its paragraphs.
There are three essential types of sources for document analysis:
#1: Public Records, such as transcripts, statements of purpose, yearly reports, strategy manuals, ebooks and so on
#2: Personal Documents, such as messages, contracts, articles, social media posts, daily papers et cetera
#3: Physical Evidence, such as flyers, publications, books or printed training materials.
Historically a good part of document analysis referred to quantitative analytics, disregarding the qualitative side. In fact, most of the applications have been related to tasks such as text labeling, frequencies, and pattern identification. However, in the last years, the rise of NLP added more value to the quantitative analysis, by adding insights about the context, and transforming simple keywords count into deeper qualitative research.
As you may have understood, this topic is connected to big data, NLP and small data.
So, if you missed our videos about these topics, now it’s the right moment to watch em all.