Semantic Incongruity Calculation for Web Content Interest Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current web browsing technologies fail to effectively predict user interest in web content, as they model users as random surfers rather than hedonic information foragers, lacking a systematic approach to identify intrinsically psychologically stimulating digital objects.
Innovation Solution
A computing system that determines the semantic incongruity of digital objects using diversity and anomalousness calculations based on semantic exemplars, such as tags or metadata, to predict user interest by quantifying the level of incongruity, which is then used to suggest interesting web content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional web browsing technologies model users as random surfers, then the system complexity remains low, but the ability to predict user interest and provide psychologically stimulating content is poor
Solution Approach 1:
The patent transforms the user model from 'random surfer' to 'hedonic information forager' by changing the underlying parameters of user behavior. This involves introducing new parameters such as semantic incongruity, diversity, and anomalousness to quantify user interest, thereby improving prediction accuracy while managing system complexity through structured computational approaches
Solution Approach 2:
The patent replaces traditional mechanical search and browsing mechanisms with a semantic-based computational system. Instead of relying on keyword matching and link following, the system uses semantic analysis of digital objects, calculating incongruity based on semantic relationships between concepts to predict user interest
2Measurement precision
If the system uses semantic incongruity calculations based on diversity and anomalousness, then the prediction of user interest improves, but the computational complexity increases
Solution Approach 1:
The patent segments the complex task of predicting user interest into distinct computational components: calculating diversity of semantic concepts, calculating anomalousness of digital objects, and combining these to determine semantic incongruity. This segmentation allows each sub-task to be handled with appropriate algorithms, managing overall computational complexity while maintaining prediction accuracy
Solution Approach 2:
The patent introduces semantic incongruity as an intermediary metric that mediates between the raw semantic data and the final user interest prediction. This intermediary concept simplifies the computational process by providing a structured way to quantify the relationship between diversity and anomalousness, making the overall system more manageable
Data Source
AI summary
A computing device may determine, based at least in part on one or more semantic exemplars associated with a digital object, a level of incongruity for the digital object, and output an indication of the level of incongruity for the digital object. For instance, a system may provide a web application that can support hedonic web surfing. By modeling Internet users as active information foragers instead of random surfers, a system may obtain quantitative measures of digital objects that users may find psychologically stimulating. The system may utilize a quantitative measure of the conceptual incongruity of digital objects that may predict how interesting users will find an object.