Abstract: Embodiments of methods and systems for incorporating user generated content into a web page are disclosed. In particular, embodiments of such systems and methods may incorporate user generated content into a web page such that the user generated content can be consumed by indexers associated with search engines in association with that web page. Additionally, embodiments may also provide a mechanism by which user generated content may be received and included in a web page when that web page is rendered. Using embodiments as disclosed herein user generated content may be exposed to a search engine indexer in a web page while still providing a mechanism for incorporating the freshest user generated content in such a web page.

Abstract: Embodiments of methods and systems for incorporating user generated content into a web page are disclosed. In particular, embodiments of such systems and methods may incorporate user generated content into a web page such that the user generated content can be consumed by indexers associated with search engines in association with that web page. Additionally, embodiments may also provide a mechanism by which user generated content may be received and included in a web page when that web page is rendered. Using embodiments as disclosed herein user generated content may be exposed to a search engine indexer in a web page while still providing a mechanism for incorporating the freshest user generated content in such a web page.

Abstract: Techniques for collecting data indicative of one or more browsing behaviors (e.g., completing a transaction on a website) are described. User generated content (UGC) that affects user behavior may be identified, such as product reviews that, if read by a user, are statistically more likely to cause that user to make a purchase. A metric may be assigned to particular user generated content, where the metric indicates an extent to which the particular user generated content is associated with a particular browsing behavior. Based on the assigned metric, particular UGC may be included in a web page. For example, the product review that is most likely to cause a user to make a purchase may be placed in a prominent location on a web page in order to increase sales and revenue. Browsing behaviors may be positive or negatively associated, and metrics assigned to UGC may be based on visibility.

Abstract: Embodiments of methods and systems for incorporating user generated content into a web page are disclosed. Certain embodiment may allow a different amount of user-generated content to be incorporated into a set of web pages associated with the same product. More particularly, according to one embodiment, a first amount of user-generated content can be presented on an initial web page associated with the product and a different amount of user generated content can be presented on subsequent pages. Moreover, in other embodiments, differing sort orders may be utilized in conjunction with the initial web page and subsequent pages with the result that the user-generated content is incorporated into the initial web page according to a first sort order and user generated content is incorporated into subsequent web pages according to a different sort order.

Abstract: Embodiments described herein provide systems and methods for brand response. One embodiment of a system for providing brand a review system configured to receive customer reviews from a plurality of web sites and provide for display on the web sites responses to the customer reviews inline with the customer reviews. The system can further include a brand response system configured to allow a user associated with a manufacturer to submit a response to a customer review of a product and provide the response to the review system.

Abstract: Non-linear classifiers and dimension reduction techniques may be applied to text classification. Non-linear classifiers such as random forest, Nyström/Fisher, and others, may be used to determine criteria usable to classify text into one of a plurality of categories. Dimension reduction techniques may also be used to reduce feature space size. Machine learning techniques may be used to develop criteria (e.g., trained models) that can be used to automatically classify text. Automatic classification rates may be improved and result in fewer numbers of text samples being unclassifiable or being incorrectly classified. User-generated content may be classified, in some embodiments.

Abstract: Systems and methods to facilitate the collection and processing of content generated by users are disclosed. Specifically, in one embodiment, user generated content may be aggregated from multiple retailers. This user generated content may be processed to obtain a variety of statistical data associated with the user generated content, including an importance metric. This importance metric may be utilized to rank the products of the manufacturer such that statistical, or other, data related to the manufacturer's products may be presented to a user in the order of product importance.

Abstract: Embodiments of methods and systems for incorporating user generated content into a web page are disclosed. In particular, embodiments of such systems and methods may incorporate user generated content into a web page such that the user generated content can be consumed by indexers associated with search engines in association with that web page. Additionally, embodiments may also provide a mechanism by which user generated content may be received and included in a web page when that web page is rendered. Using embodiments as disclosed herein user generated content may be exposed to a search engine indexer in a web page while still providing a mechanism for incorporating the freshest user generated content in such a web page.

Abstract: Embodiments of systems and methods for linking a computer device to a session that is being conducted on another computing device are disclosed. A content-generation session may be conducted by a user on a particular computing device. As part of the content-generation session, the user may request to add other content, which may be located on a different computing device, to content being authored during the content-generation session. Information to allow the different computing device to establish a link to the content-generation session may be generated. Using that information, a link may be automatically established between the different computing device and the content-generation session, such that the other content residing on the different computing device can be associated with the content-generation session.

Abstract: Systems and methods for providing a manufacturer portal are disclosed. More specifically, in one embodiment a content distribution system, as a central location for user generated content may also provide manufacturers with a portal to monitor, and participate in, the process of content generation and distribution. This portal may provide the manufacturers with the ability to: view generated content related to that manufacturer and to filter this user generated content utilizing a wide variety of criteria and to generate content which may be responsive to presented generated content. Content generated by a manufacturer through their portal may subsequently be incorporated into one or more retailer's site utilizing the content distribution system.

Abstract: Embodiments of methods and systems for incorporating user generated content into a web page are disclosed. In particular, embodiments of such systems and methods may incorporate user generated content into a web page such that the user generated content can be consumed by indexers associated with search engines in association with that web page. Additionally, embodiments may also provide a mechanism by which user generated content may be received and included in a web page when that web page is rendered. Using embodiments as disclosed herein user generated content may be exposed to a search engine indexer in a web page while still providing a mechanism for incorporating the freshest user generated content in such a web page. Embodiments may also improve the ability of search engines or search engine indexers to determine the site of origin for such user content.

Abstract: Non-linear classifiers and dimension reduction techniques may be applied to text classification. Non-linear classifiers such as random forest, Nyström/Fisher, and others, may be used to determine criteria usable to classify text into one of a plurality of categories. Dimension reduction techniques may also be used to reduce feature space size. Machine learning techniques may be used to develop criteria (e.g., trained models) that can be used to automatically classify text. Automatic classification rates may be improved and result in fewer numbers of text samples being unclassifiable or being incorrectly classified. User-generated content may be classified, in some embodiments.

Abstract: A web developer or other user may rapidly update the appearance of user generated content (UGC) or other content that appears as part of a web page. The look and feel of UGC or other content may be customized in order to provider a user of a web site with a better browsing experience, and to make the UGC's appearance consistent with other web site portions. In various embodiments, a displayed preview of content may be updated without having to communicate with an external program and/or without having to re-load a graphical rendering engine that is used to display the content preview. An API may be used to change internal data settings of a graphical rendering engine, which may enable the graphical rendering engine to avoid re-loading data or settings that have not been changed, thus speeding up user interaction.

Abstract: According to some embodiments of this disclosure, a software application running on a mobile device (e.g., a tablet or smartphone device) is provided which may be used by a sales associate in a physical store of an entity to assist a consumer in shopping for products or services. For example, the software application may be used by the associate to retrieve and display user generated content (UGC) items related to the products or services to assist the consumer in shopping. The software application may also store a browsing history for the user, and the sales associate may then transmit the browsing history to the consumer (e.g., via email or other electronic message).

Abstract: A content intelligence module may implement a sentiment analysis method to identify words or phrases from user-generated content that are associated with a particular sentiment. The method may comprise grouping or splitting text into different sentiment segments, tokenizing words or phrases and/or removing stopwords across the sentiment segments, performing a frequency analysis to count the words or phrases in each sentiment segment, scaling the frequency results across the sentiment segments where necessary, and removing commonly used words from the sentiment segments. The words or phrases that are left in a specific sentiment segment are the most-used words for that sentiment segment. The word cloud module therefore allows for very quick generation of a summary around sentiment segments. A sentiment overview containing the summary can be presented to a user in connection with a selected product or service with which the user-generated content is associated.

Abstract: Techniques for collection of user-generated content, such as reviews and/or ratings relating to products, are described. User-generated content relating to an opinion of a product may be received at a first location, such as a point of sale of the product (e.g., content may be collected by a device at a store). A record corresponding to the received user-generated content may be stored, and a reference that is usable to provide access from a second location (e.g., from computer system at a consumer's home) to modify the stored record may be provided. The provided reference may be usable by a consumer to submit additional information to the initially-submitted content and/or to revise the originally-submitted information. Authenticity-screening rules may be employed to mitigate opportunities for submission of fraudulent reviews.

Abstract: Embodiments of systems and methods for determining style attributes of a web page are disclosed. More specifically, in one embodiment, an indication of a document corresponding to a web page may be received and one or more style attributes associated with the web page determined. To determine these style attributes, a document object model (DOM) may be produced based on the document corresponding to the web page and the analyzed DOM. Information indicative of the one or more style attributes can then be generated.

Abstract: Systems and methods for distributing user-generated content are disclosed. Specifically, embodiments of the present invention may allow content to be generated by a user at a manufacturer's site with respect to a corresponding product and this content distributed to one or more retailers who sell that product such that the user-generated content may be incorporated into the retailer's site or brick and mortar location in conjunction with that product to allow consumers shopping at that retailer to access or view such user-generated content.

Abstract: A content intelligence module implementing a unique polarization algorithm may operate to identify products with polarized sentiments in user-generated content. The module may be configured to, at a first computer: calculate an overall average rating on a product across segments in a dimension; for each segment in the dimension, calculate a segment average rating, a total number of ratings, a segment distance, and a weighted variation score; calculate a total weighted variation score for the dimension; analyze a distribution of overall sentiment variation in the dimension; set a polarization score for the dimension utilizing the total weighted variation score; and repeat the above steps for each feature, each product, and each dimension to produce polarization scores. Visual representations corresponding to the polarization scores may be presented through a browser application running on a second computer communicatively connected to the first computer over a network connection.

Abstract: Techniques for determining that an opportunity to solicit content from a user are described. Such content may relate to a user's experience with goods or services purchased by the user with a financial account (e.g., a credit card). Account information and/or transaction information may be analyzed to determine that a content submission opportunity exists. After determining that a content submission opportunity exists, a link may be inserted into a financial account statement allowing the user to provide the content. Multiple content or content types may be submitted for a single purchase (e.g., for different items in a purchase). Other variations are also described.