We highlighted a few common use cases in text analytics for the Open Data Science Conference (ODSC). Our use cases for ODSC include document categorization and product reviews. Our APIs are not limited to a particular industry and are used broadly across multiple industry verticals without modification. Custom dictionaries, custom taxonomy, or specific domains are available as custom options. See the video
Document Categorization Use Case
Several of our customers maintain a large corpus of documents. Their business demands that information retrieval is quick and accurate. Since many of the documents are free-form text, this is a difficult task. Businesses need to categorize all the documents into a hierarchy with a structure. Data Ninja services adds the structure and indexing to text documents with categories, concepts, entities, and document IDs. The indexed documents can be integrated with enterprise search platforms such as Solr. We use semantic search as a data searching technique to find not only keywords, but the intent and meaning of the words used in searching for information.
Product Reviews Use Case
Product reviews are taking seriously by our customers. Product reviews contain not only the review, but the sentiment. The Data Ninja API includes categories, sentiments, entities, and a reviewer ID for each review. In the best companies, relationships to other products and categories drive additional business. Multiple relationships are difficult to visualize without a property graph. We illustrate how graphic analytics show the relationships, nodes, and properties. Popular graph databases are Oracle Spatial and Graph, and Neo4J.