Methods and apparatus for modifying a user profile for a recommendation algorithm are provided. A user is provided with electronic access to an item. The item may comprise one of a document, an article, a chart, a graphic, a report, a web page, or the like. User interaction with the item is enabled. The user interaction with the item is then electronically tracked and stored. The user's user profile used by a recommendation engine is then modified based on the tracked user interactions. The user interaction may comprise at least one of annotating, highlighting, modifying, customizing, adding comments to the item, and the like. The user modified item can be saved and details of the user interaction with the item may be used to modify the user profile. At least one of items or peer recommendations can then be provided to the user based on the modified user profile.

A method of producing search results is disclosed. The method comprises, at a computerized search engine system distinct from a client system: receiving a search request associated with a user from the client system, the search request having one or more search terms; obtaining a user profile corresponding to the user, where the user profile is generated based in part on the user's prior computing activities, comprising one or more of browsing, searching, and messaging; obtaining search results for the search request; generating a personalized snippet for at least one of the search results in accordance with the obtained user profile, the snippet comprising a text portion of the search result chosen based on at least one or more search terms and one or more terms of the obtained user profile; and transmitting the search results and personalized snippet to the client system for display.

Some aspects of this disclosure involve computation of a preference score for a certain type of food. In some embodiments described herein, measurements of affective response of at least ten users are collected. The measurements may include various values indicative of physiological signals and/or behavioral cues of the at least ten users. Each measurement of a user is taken with a sensor coupled to the user up to four hours after the user consumed the certain type of food. A preference score is computed based on the measurements. The preference score is indicative of how much the at least ten users enjoyed consuming the certain type of food and/or how well they felt after consuming the certain type of food.

A computing device can determine a decomposition of data of actions of a first session based at least in part on a first computational model associating the actions of the first session with corresponding state values of the first session. The computing device can determine a second computational model based at least in part on the decomposition and an operation template. The computing device can receive a query via the communications interface, the query associated with the second session. The computing device can determine a state value of the second session based at least in part on the query. The computing device can operate the second computational model to determine at least one response associated with the query based at least in part on the state value of the second session. The computing device can provide an indication of the at least one response via the communications interface.

An online system maintains information identify a context in which sponsored content items were presented to users. A context in which a sponsored content item was presented to a user identifies additional content presented to the user prior to the sponsored content item, and may identify additional content presented in conjunction with the sponsored content item. The online system identifies users to whom at least one sponsored content item was presented in a context and generates characteristics for the context based on characteristics of users who were presented with at least one sponsored content item in the context. When the online system receives a request to present sponsored content items in the context that does not identify an online system user, the online system selects sponsored content items for the request based on the generated characteristics for the context.

This technology is directed to determining a character or personality characteristic for users of an online community, for example, a social network, and assigning a character or personality class to the users. In some instances, the systems and methods may determine the character or personality characteristic either implicitly from user data or actions, etc., or explicitly, by providing users with a personality survey or questionnaire to solicit responses. The system and methods assign a suitable character or personality class to the users based on the character and personality characteristic determined for the users, and generate at least one of a class description, a career profile, and a relationship profile for the users, and provide data including the class description, career profile, and the relationship profile capable of being displayed on a user interface.

A software function verification system and a software function verification method are provided. The system includes a first database, a document acquisition device, and a function verification device. The function verification device analyzes a first-party document according to a machine learning technology to generate a plurality of first-party technology points and converts the first-party technology points into a first-party decision table. The function verification device analyzes a second-party document to generate a plurality of second-party technology points and converts the second-party technology points into a second-party decision table. The function verification device respectively converts the first-party decision table and the second-party decision table into a first-party tree structure and a second-party tree structure and compares the first-party tree structure and the second-party tree structure to determine the degree of functional differences between the first-party document and the second-party document.

In an example embodiment, a plurality of labeled training documents is obtained, each labeled training document containing a plurality of text snippets. Then, a first set of features is extracted from each text snippet in each of the plurality of labeled training documents. The extracted first set of features and the plurality of labeled training documents are passed to a supervised machine learning algorithm to train a potential snippet relevance score model. A second set of features is extracted from each of a plurality of candidate text snippets in a candidate document. Then, a relevancy score is calculated for each of the plurality of candidate text snippets using the potential snippet relevance score model. Then, one of the plurality of candidate text snippets is selected to display based on the calculated relevancy scores.

A machine-implemented method for supporting a natural language user request against a user's personal data cloud can include a machine receiving the natural language user request from the user, determining a semantic interpretation of the natural language user request, querying a semantically-indexed, integrated knowledge store based on the semantic interpretation, and responding to the natural language user request by displaying results of the querying, wherein the results correspond to an item within the user's personal data cloud.

Natural language processing (NLP) with awareness of textual polarity. An NLP system, such as a search engine or a Question-Answering (QA) system receives input text for processing. The input text may be a text fragment, a search phrase, a question having a general type, or a polar question having a yes or no answer. The NLP system identifies textual polarity and provides responses to the input text (for example, in answer form) based on identifying evidence whose selection, scoring, and processing, is informed by the textual polarity of the input text, and the textual polarity of candidate evidence passages.