Analyzing distributed group discussions
Inventors
Browning, Randolph • Snelling, David Aaron • Papp, Stefan Nicholas • Zimmermann, Bernhard G. • Downs, Oliver B.
Assignees
Publication Number
US-9674128-B1
Publication Date
2017-06-06
Expiration Date
2033-03-06
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Abstract
Techniques are described for analyzing user-supplied information, including in at least some situations to predict future aspects of additional related information that will be supplied by users. The user-supplied information that is analyzed may, for example, include distributed group discussions that involve numerous users and occur via user comments made to one or more social networking sites and/or other computer-accessible sites. The analysis of user-supplied information may, for example, include determining particular topics that are of interest for a specified category during one or more periods of time, quantifying an amount of user interest in particular topics and the category during the period of time, predicting future amounts of user interest in the particular topics and the category during one or more future period of times, and taking one or more further actions based on the predicted information.
Core Innovation
The invention provides techniques for automated analysis of user-supplied information, such as distributed group discussions occurring via user comments across multiple social networking and other computer-accessible sites. The analysis identifies topics of interest from these comments during specific time periods, quantifies user interest in topics and categories, predicts expected future levels of user participation, and takes further actions based on these predictions.
The approach includes collecting user comments from diverse data sources, including but not limited to social networking services, emails, chat messages, and other communication platforms. These comments are analyzed to create topic-based comment groups, which are then categorized. Quantitative measures, such as the number of comments matching topics or categories, are used to establish trends over time and to forecast future discussion dynamics.
A key aspect of the invention is the automated, rule-based filtration of comment groups to manage over-inclusion or under-inclusion, providing a focused set of topics per category. The system can also generate prediction templates and trend lines using historical comment data and actual observed behavior to improve the accuracy of the forecasting process concerning future group discussions. This enables timely and relevant insights about distributed group communications, overcoming challenges with the distributed nature of online discussions.
Claims Coverage
There are three independent claims in this patent, each reciting a computer-implemented method, a non-transitory computer-readable medium, and a system for analyzing user-supplied content to identify and track topics and categories, perform filtering, and manage automated predictions or output.
Automated categorization and topic determination from distributed user comments
The method provides for: - Analyzing a plurality of user-supplied textual comments from multiple geographical locations and information services within a time period to identify discussed topics. - Automatically generating comment groups per identified topic, including relevant comments. - Determining subsets of topics associated with a specified content category for the period, involving inclusion/exclusion thresholds to filter comment groups based on their relative frequency in the data. - Providing indications of multiple topics representing the specified category for the period. - Tracking and reporting changes related to topic discussion across time periods, geographical locations, or information sources.
Analysis and grouping of user-supplied content by attribute on a computer-readable medium
This feature covers: - Analyzing user-supplied content items to identify a plurality of attributes, which may be topics, tags, locations, data sources, or users. - Generating comment groups based on these attributes. - Identifying content items associated with a content category, initially included in multiple comment groups. - Filtering comment groups for relevance using minimum and maximum threshold limits. - Providing information that identifies determined topics for the category based on attributes of included comment groups.
System for determining and tracking category-based topics in distributed discussions
This feature includes: - At least one hardware processor and one or more modules. - Modules are configured to analyze user-supplied content items, identify their attributes, determine a subset of topics corresponding to a content category, and filter via inclusion/exclusion thresholds. - Modules provide topic indications, track topic changes over different periods, and output information about these changes.
Collectively, the independent claims protect systems, methods, and media for automated topic extraction, relevance-based grouping, and dynamic predictive tracking of distributed user discussions across multiple content sources and time periods using threshold-based group filtering.
Stated Advantages
Provides timely and automated analysis of distributed user discussions, overcoming challenges of aggregating data from multiple, decentralized sources.
Enables accurate identification and tracking of relevant topics and categories within large-scale user-supplied content.
Facilitates prediction of future discussion dynamics and user interest using historical and real-time data.
Supports automated actions or notifications based on analyzed or predicted information, potentially enhancing client responsiveness.
Documented Applications
Assessment and prediction of distributed group discussions occurring via user comments on social networking sites and other computer-accessible platforms.
Providing clients or entities with timely information or predictions regarding user interest, discussion topics, and future trends based on group discussions.
Supplying additional comments or information to relevant platforms, potentially to influence future directions of discussions or support advertising or client-driven interventions.
Interested in licensing this patent?