Learn why and how a Knowledge Graph boosts significantly Text Analytics processes and practices and makes text work for us in a more meaningful way.
The world of text is transforming. New tools, practices and environments change the way we access, read and write text. Documents, linear as they were before, are now becoming multidimensional digital spaces to be navigated and made sense of. The text in these documents is also changing. It is coming ever closer to the exciting molecular model Nicholas Negroponte, a pioneer in the field of computer-aided design and co-founder of the MIT Media Lab, envisioned in the early 1980s:
The structure of text should be imagined like a complex molecular model. Chunks of information can be reordered, sentences expanded, and words given definitions on the spot […]. These linkages can be embedded either by the author at “publishing” time or later by readers over time. Think of hypermedia as a collection of elastic messages that can stretch and shrink in accordance with the reader’s actions. Ideas can be opened and analyzed at multiple levels of detail. Negroponte, Being Digital, p.70
Today’s technologies for manipulating, organizing and creating text are bringing our textual experiences and environments closer to Negroponte’s vision. Different technologies approach the tasks differently but here we want to talk about text analytics combined with content enrichment.
Content enrichment, or semantic annotation, is about attaching names, attributes, comments, descriptions to a whole document, document snippets, phrases or words. It provides additional information (metadata) about an existing piece of text and thus enriches the unstructured or semi-structured data with context that is further linked to the domain structured knowledge.
With text analytics and content enrichment, we can think of text as separate digital objects relating to each other. What’s more, the interactions and connections between them can be, if not computed in their entirety, at least mapped and interlinked for smarter use. As a result of all that, we can now afford to think about texts outside the page and the nimble delivery of “elastic messages”, envisioned by Negroponte.
It is when text analytics processes are enhanced with content enrichment techniques that textual information goes beyond the page metaphor to become a digital space to access, navigate and modify with ease.
Connecting parts of a text to a broader machine-readable context, allows both authors and readers to organize, search and store information in novel, more efficient and more intriguing, molecular-model ways. This empowers tasks such as search and retrieval, indexing and classification, sharing and recommendation.
In an enterprise context, taking text analytics to the next level with content enrichment can be applied to cost-effective integration and management of digital assets. Content then is freed from the confines of the page and enters a world of machine-readable textual chunks where concepts are interconnected in a myriad of combinations.
Case in point, the unified semantic publishing platform Euromoney built to enhance their content production.
Several years ago, Euromoney was faced with the challenge of streamlining content produced daily throughout the company’s 84 business units. Such an endeavor required a single, consolidated platform for authoring, storing and retrieving that content. It also had to provide capacities that allowed effective reuse and repurposing of content – not only across the company’s properties for external communication but also for internal use, across departments.
The challenge was solved by creating a text analytics solution that involved content enrichment (more specifically a combination of an RDF database and an automated semantic annotation pipeline, about which you can read in our use case: Euromoney: Improving Content Production Through a Unified Semantic Publishing Platform). This was not an out-of-the-box solution, but involved processes and workflows built from scratch and tailored to the unique Euromoney’s use case.
Within Euromoney’s sophisticated new publishing and information platform, each concept was automatically identified and stored in the form of a semantic fact that was further linked to the document it belonged to. Thus, on one hand, Euromoney authors were able to access semantically enriched content and, on the other, readers gained access to better classification and recommendation of the content they consumed.
Enterprise-wide, text analytics boosted with content enrichment opened electronic doors for content, that allowed:
Immersive environments of textual information beyond the notions of the print culture and into the world of the radically different molecular model of text are what we all want to have. In an enterprise context, this translates into better text authoring, delivery and navigation tools. Good knowledge management starts with well-orchestrated text delivery across all business units, platforms and devices.
Complementing text analytics with the processes of content enrichment is what can bring us towards not only a more efficient text manipulation and navigation but also closer to richer experiences in the predominantly text-based environments we work in.
Do you need help tailoring text analytics to your particular use case?
White Paper: Text Analytics for Enterprise Use
Use the power of text analytics for your enterprise