Group items tagged

TextAnalyst processes textual data through what is termed "natural language text analysis." Using linguistic rules and "artificial neural network technology," the program mimics human cognitive analytical processes. It begins by processing each document as a sequence of symbols, generating a hierarchical semantic network structure based on the frequency of terms and the relationships between them. After analyzing the document, each term (or theme) within the network is assigned an individual statistical weight (range 0-100) relative to its importance within the entire text. Additionally, the relationships between terms are also assigned a statistical weight, in effect highlighting the strength of thematic associations. TextAnalyst then engages in the process of renormalization - adjusting the statistical weight of each term based on its relationship to others. The renormalized values are termed "semantic weights" and can be arranged into a semantic network. High semantic weights are indicative of a term or theme having considerable significance within the overall text. Inter-item weights, also presented in the figures to follow, suggest significant association between text themes.

TextAnalyst processes textual data through what is termed "natural language text analysis." Using linguistic rules and "artificial neural network technology," the program mimics human cognitive analytical processes. It begins by processing each document as a sequence of symbols, generating a hierarchical semantic network structure based on the frequency of terms and the relationships between them. After analyzing the document, each term (or theme) within the network is assigned an individual statistical weight (range 0-100) relative to its importance within the entire text. Additionally, the relationships between terms are also assigned a statistical weight, in effect highlighting the strength of thematic associations. TextAnalyst then engages in the process of renormalization - adjusting the statistical weight of each term based on its relationship to others. The renormalized values are termed "semantic weights" and can be arranged into a semantic network. High semantic weights are indicative of a term or theme having considerable significance within the overall text. Inter-item weights, also presented in the figures to follow, suggest significant association between text themes.

Semantic tags are added manually, or automatically if the item is a photo from Flickr or a video from YouTube. "We add a new level of order to connect and interact with these things at a higher level than is possible today," Spivack says. "We are letting you build a little semantic Web for your project, your group, or your interest." When it's done, it should be like the best wiki you've ever used. To illustrate, Spivack flips open his computer and pulls up his own Radar-enabled page.