The content analytics miner provides multiple ways for you to explore, analyze, and compare all of the information in a collection. You can use this information to gain insight into your enterprise data. For example, you might use the analysis results to improve decision making, provide more efficient and effective customer support, identify competitive strengths or weaknesses, or detect potential problems before they occur. With content analytics, you can search enterprise resources and draw meaningful insights from the search results.
The content analytics miner supports simple keyword searches and complex query syntax. After you search a collection, you select various views to further analyze and see correlations between the results. As you view the analysis results, you can iteratively fine tune your query, zoom in on particular items of interest, and expand or narrow the set of documents that you want to focus on.
To help you analyze the results of linguistic processing and text analysis, IBM® Watson Content Analytics organizes and classifies documents that share similar patterns or content. Facets represent the different aspects or dimensions of the documents in your collection. Some facets are hierarchical and contain one or more levels of subfacets. For example, the facet for a car manufacturer might have subfacets that represent the various vehicle models, model years, and cities of manufacture.
Each facet is associated with one or more values. Facet values are usually words and phrases that are extracted from your textual content. Facet values can also be obtained from structured fields such as date or numeric fields.
Facets provide a mechanism for navigating and analyzing your content with the content analytics miner. In a content analytics collection, you select facets to explore content. In real-time, you can search across all facets to explore analysis results, relationships, and how different facets of your content change over time.