Categorization & Text Analytics

Synaptica’s Text Analytics Platform (TAP)

Synaptica’s Text Analytics Platform (TAP) is text analytics and auto-categorization made simple. Fully integrated with Synaptica’s KMS enterprise taxonomy management system, TAP is a text analytics and auto-categorization module for the analysis and classification of structured and unstructured information.

Dive deeper into unstructured content with text analytics solutions. Synaptica’s guiding principle is simplicity of use while delivering complex and advanced functionality for the development of text analytics applications. At Synaptica, we believe complexity doesn’t have to be complex.

Simple UI

TAP's innovative design tackles common pain-points:

- Compress the learning curve through simple user interfaces that help taxonomists become fluent in categorization without having to learn esoteric syntax.

- Categorization rules are fully transparent and easily editable. The no-black-box principle helps users understand how auto-categorization works and to refine indexing rules.

- Integrate systems and synchronize the taxonomy management and categorization processes.

- The no-silo approach reduces complexity and improves productivity.

Taxonomy-Based Text Analytics

Synaptica’s Text Analytics solutions start with your enterprise taxonomy. Text analytics use your organization’s vocabularies to automatically apply metadata to corporate content for knowledge management.

Categorization enables an enterprise to sort and rank content based on what it is about. TAP indexes, classifies, and applies metadata to content using authoritative concepts and named entities defined within enterprise taxonomies in the Knowledge Organization System (KOS). The tagging process leverages the semantic definitions and structure of the KOS to contextualize the meaning of the words and phrases found in documents. Aboutness algorithms rank the most relevant concepts and names within individual documents and across collections. Generalization algorithms group content into broad categories while salience algorithms identify what sets particular documents apart from the rest.

Document Sections

Content Types & Document Sections allow users to quickly and flexibly define document type templates by specifying tags, text, and other document markers to improve weighted relevancy ranking. Document sections provide context for found concepts and allow for the application of weights to score these concepts appropriately. The output is a clearly defined list of concepts, where they appear, and a document section score.