Abstract: A computer-implemented method according to one embodiment includes receiving a first set of inputs from a first plurality of users. A history of interactions and/or collaborations of a first group of users of the first plurality of users is accessed. A latent class model of the first plurality of users is generated using information obtained from the accessing. It is determined from the latent class model whether any of the first plurality of users exceed a predetermined threshold of relatability. Users of the first plurality of users that are determined to exceed the predetermined threshold are allowed access to a generated first state of a forum. Users of the first plurality of users that are determined to not exceed the predetermined threshold and the users of the first plurality of users that are determined to exceed the predetermined threshold are allowed access to a generated second state of the forum.

Abstract: Methods and systems are disclosed for determining gaps in a user's resume regarding skills or titles for a job, and recommending educational courses to the user based on those gaps. The user's resume is received and analyzed for the user's current set of skills. Various searching methods are used to identify a set of job requisitions based on a user's input query for a job. The user's skills are compared with a set of required skills associated with the set of job requisitions. Educational courses are identified for the skills that are required for the set of job requisitions but are not present in the user's set of skills. The educational courses presented to the user via the search engine. The user's resume can also be ranked relative to other resumes for the skills or titles required for a job.

Abstract: The present disclosure contemplates a variety of improved methods and systems for providing professionals and organizations tools to improve productivity and efficiency. The present disclosure includes a process for discovering and validating entity objectives. In an embodiment, the method and system receive communications from multiple data sources (e.g., email, calendar, contacts), find correlations between the communications, identify communications that appear to be important to a user, and provide relevant resources.

Abstract: A recommendation platform that provides a menu of automated recommendations from on-line information by friends, with various weighting factors, to evaluate businesses. The platform is a software deployable system that amalgamates the candidate businesses into different categories and cross-references friends' experiences with these businesses. The interface utilizes a circular-like menu and is both compact and easily navigable.

Abstract: A microprocessor executable method and system for determining the semantic relatedness and meaning between at least two natural language sources is described in a prescribed context. Portions of natural languages are vectorized and mathematically processed to express relatedness as a calculated metric. The metric is associable to the natural language sources to graphically present the level of relatedness between at least two natural language sources. The metric may be re-determined with algorithms designed to compare the natural language sources with a knowledge data bank so the calculated metric can be ascertained with a higher level of certainty.

Abstract: Methods, systems and computer program products are provided for determining acoustic feature vectors of query and target items in a first vector space, and mapping the acoustic feature vectors to a second vector space having a lower dimension. The distribution of vectors in the second vector space can then be used to identify items from the same songs, and/or items that are complementary. A mapping function is trained using a machine learning algorithm, such that complementary audio items are closer in the second vector space than the first, according to a given distance metric.

Abstract: A content server system provides content items to a plurality of users in a content stream. The content server system provides an interface to collect feedback from the plurality of users on the content items in the content stream. Based on the collected feedback the content server system generates a feedback model that predicts the likelihood of receiving feedback on a content item at any given time in a streaming session. The content server system then selects a content item in need of feedback and, using the model, determines a time at which the content item is more likely to receive feedback. The content server system then provides the content item to the user at the determined time.

Abstract: Embodiments of the present disclosure are directed to providing a more accurate presentation of a vehicle's surroundings when the presentation combines images from multiple cameras. Cameras may capture the same portion of the environment. If an object is within view of at least two cameras, each camera produces a portion of an overall view, such as a 360 degree synthetic top-down view. The seam, angle and/or geometry, angle between any two images is dynamically determined, such as due to proximity (or lack thereof) to an object. As a result the synthetic top-down view may present an image of an object more prominently and/or avoid having the seam between camera images fall on the image of the object, which may otherwise result in the image of the object being omitted from both camera images.

Abstract: Embodiments provide a computer implemented method in a data processing system comprising a processor and a memory comprising instructions, which are executed by the processor to cause the processor to implement the method of identifying negative communications from a plurality of electronic communications, including: extracting a plurality of terms from the plurality of electronic communications, wherein the plurality of terms include subjects, action verbs, adjectives and business objects; identifying variations of each term and grouping the variations for each term to form a dictionary; generating a co-occurrence graph to illustrate relationships between different terms in the plurality of terms; assigning each term with an entity type; identifying an intent for each business object using the co-occurrence graph; providing one or more rules, and identifying one or more negative communications based on the one or more rules.

Abstract: A presence mimicking system comprises a first lighting system (1A) arranged to illuminate a first environment and a second lighting system (1B) arranged to illuminate a second environment. A computer system configured to receive from the first lighting system an indication of a sequence of illumination settings, at least some of which have been applied to the first lighting system by at least one user when present in a first environment illuminated thereby. The computer system is configured, in response to a mimic instruction, to mimic in the unoccupied second environment the presence of the at least one user of the first environment, by applying a matching sequence of illumination settings to the second lighting system, wherein the computer system is configured to select the first lighting system for use in the presence mimicking from a set of candidate lighting systems, by comparing a profile of the second lighting system with profiles of the candidate lighting systems.

Abstract: Disclosed is a method for suggesting revisions to a document-under-analysis (“DUA”) from a seed database, the seed database including a plurality of original texts each respectively associated with one of a plurality of final texts. The method includes tokenizing the DUA into a plurality of statements-under-analysis (“SUAs”), selecting a first SUA of the plurality of SUAs, generating a first similarity score for each of the plurality of the original texts, the similarity score representing a degree of similarity between the first SUA and each of the original texts, selecting a first candidate original text of the plurality of the original texts, and creating an edited SUA (“ESUA”) by modifying a copy of the first SUA consistent with a first candidate final text associated with the first candidate original text.

Abstract: A system and method are provided for summarizing multiple aspects of tags associated with media events. In the system and method, tag metadata for tags generated at one or more user interfaces associated with at least one media event is obtained. Thereafter, tags are organized into a hierarchy of tags based on the metadata and a metadata sorting criteria. Additionally, tag significance data for tags is computed based on the metadata and the hierarchy. A visual representation of the tags can then be generated, where indicia for the tags is spatially arranged to visually depict the hierarchy of the tags are selected to visually depict at least a relative significance among sibling tags in the hierarchy.

Abstract: A method which facilitates the offering and subscription to infoservices and sending of information to subscribers based on web feeds is disclosed. In an embodiment of the invention only a link is placed on a website allowing any visitor/readers to subscribe to receive newly published content of that website, without the owner of that website having to take any additional steps to offer this infoservice. Subscribers can choose which messages they want to receive, for example only messages which are linked to certain tags or contain certain keywords, and how they should be delivered, for example by email, mobile, news page or web feed. The central infoservices platform additionally allows publishers of the infoservice's underlying web feed to prove ownership of the infoservice's underlying website or web feed, and providing publishers access to the collected information about subscribers of the infoservice.

Abstract: Systems and methods for processing qualitative responses from a plurality of user devices whereby a selection of a next thought object, to deliver to a first user device, may be based on a plurality of qualitative responses received from a plurality of user devices. In a preferred embodiment, a thought object selection computer may compute the selection by determining a filtered set of thought objects by custom selection. In some embodiments, if the quantity of the filtered set of thought objects is greater than a pre-configured amount the selection may be computed by randomly selecting a subset of the filtered set of thought objects. Further filtering the filtered set of thought objects by determining one or more least seen thought objects, and selecting a most diverse thought object, updating the filtered set of thought objects and sending the filtered set of thought objects to the first user device.

Abstract: An endpoint computer system monitors data relating to a plurality of events occurring within an operating environment of the endpoint computer system. The monitoring can include receiving and/or inferring the data using one or more sensors executing on the endpoint computer system. The endpoint computer system can store artifacts used in connection with the plurality of events in a vault maintained on such endpoint computer system. The endpoint computer system, in response to a trigger, identifies and retrieves metadata characterizing artifacts associated with the trigger from the vault. Such identified and retrieved metadata is then provided by the endpoint computer system to a remote server.

Abstract: Systems and methods for collaborative creation of content snippets are disclosed. In embodiments, a method of the invention includes: receiving, by a computing device, indications from multiple users over time that content is of value, wherein the indications are in the form of computer-based actions from multiple user devices monitored by the computing device; dynamically generating, by the computing device, a collaborative snippet based on the indications from the multiple users, wherein the collaborative snippet is auto-tagged by the computing device with context data such that the collaborative snippet includes one or more tags; and saving, by the computing device, the collaborative snippet in a snippet database.

Abstract: Prioritizing items based on user activity includes determining a user interest based on a current user activity and prioritizing items in a list presented in a display based on the user interest.

Abstract: Text including at least a first term can be presented on a display. A first score can be determined for the first term. The first score can be based, at least in part, on a lifecycle of the first term. The first score can be assigned to a first data value. The first data value can be presented on the display.

Abstract: In one embodiment, a method includes identifying one or more place-entity nodes in a heterogeneous graph, wherein the heterogenous graph comprises place-entity nodes, user nodes, and n-gram nodes, and wherein each place-entity node corresponds to a place-entity associated with a particular geographic location, assigning, for each identified place-entity node, an initial quality-score for the place-entity node, and calculating, for each identified place-entity node, a final quality-score for the identified place-entity node, wherein each final quality-score is calculated by iteratively propagating the initial quality-scores corresponding to the identified place-entity nodes, respectively, through the place-entity nodes, n-gram nodes, and user nodes of the heterogeneous graph until the quality-scores associated with the place-entity nodes, n-gram nodes, and user nodes reach convergence.

Abstract: Computer implemented methods for storing ad hoc relations between previously unrelated database objects assigned to different database structures using an electronic computing device are presented, the methods including: causing the electronic computing device to define at least three database structures: structure A, structure B and structure C, where each of the at least three database structures each includes a number of objects, where there exists at least one relation between objects of structure A and objects of structure B, and where there exists at least one relation between objects of structure B and objects of structure C; filtering data of structure A; accessing structure B using a first selected relation between structure A and structure B; storing information about filtering of structure A and information on a first selected path between structure A and structure B; filtering results obtained from structure B.

Abstract: Methods, systems, and apparatus to constrain a search are described. A selection of one or more items of a search result set by a user may be obtained. One or more attributes of the one or more selected items may be evaluated. One or more filters are identified based on the evaluated attributes.

Abstract: A computer-implemented method includes receiving a query referencing entities, and determining non-polar questions (NPQs) for the query. Each of the NPQs omits a respective target entity (TE) of the entities. The method includes determining, for each of the NPQs, whether the NPQ is a non-matching NPQ by determining whether a top ranked answer for the NPQ matches the TE of the NPQ. The method includes proceeding to determine an updated input statement (UIS) for a non-matching NPQ by replacing the TE of the non-matching NPQs with the top ranked answer for the non-matching NPQ, determine an updated NPQ for the UIS, and determine whether the top ranked answer for the updated NPQ matches the TE of the updated NPQ, in an iterative or recursive manner. The method includes outputting a UIS as a substitute statement for the query.

Abstract: A method of collecting and organizing online resources may include selecting an item from an electronic document. The method may include extracting data related to the item from the electronic document. The method may include identifying whether a first list that includes the item is associated with the electronic document. The method may include refining the first list in response to an identification of the first list. The method may include generating a second list that includes the item in response to a failure to identify the first list. The method may include verifying that the first list is consistent with a user interest. The method may include saving the first list to an electronic data storage device when the first list is consistent with the user interest. The method may include selecting a second item when the first list is inconsistent with the user interest.

Abstract: A computing device receives training data representing different observations where each observation is categorized into one of options for a target variable. The device obtains computer command(s) for categorizing into one of the options for the target variable. The device generates a sampling scheme for sampling terms of the training data. The device generates sampling models by, for N iterations of the sampling scheme: determining a subset of the training data based on a training data index; sampling, based on a term index, the subset of the training data for a subset of terms; and generating, based on the subset of terms, a sampling model for categorizing, according to the computer command(s). Each sampling model is generated from a different subset of terms such that the sampling models are randomized. The device computes an aggregated model for categorizing test data into one of the options for the target variable.

Abstract: According to an embodiment, a moving object tracking apparatus includes an acquiring unit, an associating unit, and an output control unit. The acquiring unit is configured to acquire a plurality of pieces of moving object information representing a moving object included in a photographed image. The associating unit is configured to execute an associating process for associating a plurality of pieces of the moving object information similar to each other as the moving object information of the same moving object for three or more pieces of the moving object information. The output control unit is configured to output the associated moving object information.

Abstract: An affective summarization system provides affective text summaries directed towards affective preferences of a user, such as psychological or linguistic preferences. The affective summarization system includes a summarization neural network and an affect predictor neural network. The affect predictor neural network is trained to provide a target affect level based on a word sequence, such as a word sequence for an article or other text document. The summarization neural network is trained to provide a summary sequence based on the target affect level and on the word sequence for the text document.

Abstract: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Abstract: An approach is provided in which an information handling system receives a request to publish a set of content data. Prior to publishing a set of content data, the information handling system evaluates a set of audio data and a set of video data included in the set of content data against a content knowledge base and generates an unsuitability ranking of the set of content data. When the unsuitability ranking exceeds a first predetermined threshold, the information handling system prohibits publication of the set of content data. When the unsuitability ranking is below a second predetermined threshold, the information handling system publishes the set of content data.

Abstract: A method for operating a data processing system to identify documents in a library includes a plurality of documents and a plurality of concepts exemplified by the plurality of documents and computer readable media that stores instructions for causing a data processing system to execute that method are disclosed. The method includes causing the data processing system to identify candidate documents matching a user provided search keyword from the library, causing the data processing system to generate a topical graph relating concepts contained in the candidate documents to one another, and clustering the candidate documents based on the topical graph. For each cluster, the data processing system displays a summary of the candidate documents in that cluster together with a cluster name that characterizes that cluster.

Abstract: Methods and systems that create domain influence scores that can be used to rank or sort search results are described. In one embodiment, a domain influence scoring system begins by preselecting a subset of the domains and allocating an initial influence score to only the domains in the subset while all other domains have an initial influence score of zero. Then links to pages are counted to update the influence scores of each domain. Further, one or more blacklists can be used to modify updating of the influence scores.

Abstract: A project support system supports the smooth operation of a project. For each predetermined unit that a project comprises, a model case which prescribes a target for each consensus-building task, and an ideal execution time and execution method for each of the consensus-building tasks based on the performance of each consensus-building task executed in a previous project is generated. A consensus building plan which prescribes, for each of the predetermined units, a target, an execution time and an execution method for each of the consensus-building tasks which are to be executed in a current project based on information of the current project and the corresponding model case is generated.

Abstract: A novel data-parallel algorithm is presented for topic modeling on a highly-parallel hardware architectures. The algorithm is a Markov-Chain Monte Carlo algorithm used to estimate the parameters of the LDA topic model. This algorithm is based on a highly parallel partially-collapsed Gibbs sampler, but replaces a stochastic step that draws from a distribution with an optimization step that computes the mean of the distribution directly and deterministically. This algorithm is correct, it is statistically performant, and it is faster than state-of-the art algorithms because it can exploit the massive amounts of parallelism by processing the algorithm on a highly-parallel architecture, such as a GPU. Furthermore, the partially-collapsed Gibbs sampler converges about as fast as the collapsed Gibbs sampler and identifies solutions that are as good, or even better, as the collapsed Gibbs sampler.

Abstract: In an example implementation, a method includes receiving, at a computing device, borrower information, requested financing plan information, and credit bureau information relating to a particular borrower. Likewise, a method includes processing at least one of the received information to identify a subset of lenders as potential candidates to approve a loan for the particular borrower and generate an offer of the loan for the borrower. Further, the method includes performing a portfolio assignment process and generating electronic documents relating to the loan following the borrower's acceptance of the offer. Finally, the method includes sending an offer of the loan to a borrower and, upon receipt of the borrower's acceptance, transmitting the loan documents to the borrower.

Abstract: An online system receives multiple candidate components for including in content items to be presented to online system users. Upon identifying an opportunity to present content to a subject user of the online system, the online system dynamically generates an optimal content item for presentation to the subject user that includes one or more candidate components. Candidate components included in the optimal content item are selected by predicting an affinity of the subject user for each candidate component. The affinity of the subject user for a candidate component may be predicted using a machine-learned model that is trained using historical performance information about content items including the candidate component that were presented to viewing users of the online system having at least a threshold measure of similarity to the subject user. Components of content items used to train the model may be selected using a heuristic (e.g., Thompson sampling).

Abstract: For a visit of a user to a web page where the user's identity on an online system is not presently known to the online system, the online system uses a machine learning model to make a prediction of the user's identity. The online system obtains visit data about the visit of the user to the web page. The online system identifies candidate user IDs that may represent the user, based on the visit data and data known about previous visits of the candidate user IDs. The online system derives visit features for each candidate user ID based on a relationship between the current visit data and previous visit data for the candidate user ID. The online system provides the visit features for each candidate user ID to a prediction model that determines whether, or how likely, the candidate user ID accurately identifies the visiting user, and based on the determinations selects one of the candidate user IDs as the most likely user ID for the visiting user.

Abstract: A method, system, and computer program product, include receiving a first input at a first element among a plurality of elements associated with at least one electronic document, determining a second element associated with the first element from the plurality of elements based on predetermined relations of the plurality of elements, and causing a view to be displayed together with an electronic document including the first element, the view at least including the second element.

Abstract: In an example embodiment, a machine learning algorithm is used to train a deep semantic similarity neural network to output a semantic similarity score between a candidate job search query and a candidate job search result. This semantic similarity score can then be used in a ranking phase to rank job search results in response to a first job search query.

Abstract: Disclosed is a method for suggesting revisions to a document-under-analysis (“DUA”) from a seed database, the seed database including a plurality of original texts each respectively associated with one of a plurality of final texts. The method includes tokenizing the DUA into a plurality of statements-under-analysis (“SUAs”), selecting a first SUA of the plurality of SUAs, generating a first similarity score for each of the plurality of the original texts, the similarity score representing a degree of similarity between the first SUA and each of the original texts, selecting a first candidate original text of the plurality of the original texts, and creating an edited SUA (“ESUA”) by modifying a copy of the first SUA consistent with a first candidate final text associated with the first candidate original text.

Abstract: Systems, methods and media for purchasing and commenting on identified products in media content are provided. In one example, a method comprises receiving media content from a content source and accessing data relating to an aspect of the media content, such as a product or service shown in the media content. The media content is communicated to first and second display devices for presentation to respective first and second users, and the data relating to an aspect of the media content is also sent to the first and second devices for presentation to the first and second users at about the same time. User commentary generated by the first or second user associated with the media content or the data relating to an aspect of the media content is received from the first or second device.

Abstract: Each of a plurality of endpoint computer systems monitors data relating to a plurality of events occurring within an operating environment of the corresponding endpoint computer system. The monitoring can include receiving and/or inferring the data using one or more sensors executing on the endpoint computer systems Thereafter, for each endpoint computer system, artifacts used in connection with the events are stored in a vault maintained on such endpoint computer system. A query is later received by at least a subset of the plurality of endpoint computer systems from a server. Such endpoint computer systems, in response, identify and retrieve artifacts within the corresponding vaults response to the query. Results responsive to the query including or characterizing the identified artifacts is then provided by the endpoint computer systems receiving the query to the server.

Abstract: Described is a system that matches a query with a set of sentences. When a query is received, the system may extract features from the query including one or more words as tokens and retrieve a set of candidate sentences as potential results for the query. For example, the query may be in the form of a question, and the candidate sentences may be alternative phrasings of the query that potentially match the user's search intent. The relevant set of candidate sentences may be determined based on using multiple relevancy scores and the system may rank the candidates according to an overall or aggregate score. Accordingly, the set of results to a query may be provided by recognizing the sentence as a whole and, for example when the query is a question, the interrogative intent of the query.

Abstract: A method for determining reach of a content item that is displayed on one or more client devices associated with at least one unresolved identifier. An unresolved identifier defines a context in which a client device accesses one or more online systems, the context not determined to be associated with a specific user. The method comprises identifying a set of unresolved identifiers, and identifying information describing one or more access events associated with each unresolved identifier. For each pair of unresolved identifiers, a similarity score for the pair is determined based on the identified information. Responsive to the similarity score exceeding a threshold similarity score, the pair of unresolved identifiers is clustered, the clustering indicating a prediction that the pair of unresolved identifiers are associated with a common user. Finally, for the reach of the displayed content item is determined based on the clustering of the set of unresolved identifiers.

Abstract: Disclosed are methods and systems for a data discovery solution which harnesses the power of crowdsourcing to improve automated data curation. This is done in two complimentary ways: (a) large scale collective curation through anonymized multi-tenancy, and (b) and through internet scale matching and validation gaming platform using mobile application game. The result is the most extensive library of semantic-technical mappings of the enterprise data, which are immediately at hand to provide a fast, easy and a good understanding of the enterprise data. The data discovery solution forms a gateway for governing and unlocking value from big data.

Abstract: In one embodiment, a method includes receiving, by one or more computing devices of an online social network, from a client system of a first user of the online social network, a query inputted by the first user. The method further includes accessing a social graph of the online social network, the social graph including multiple nodes and multiple edges connecting the nodes, each node corresponding to an entity associated with the online social network. The method also includes identifying multiple entities matching the query, each identified entity having a duplication-value with respect to a canonical-entity, the duplication-values being based on a name similarity between the identified entity and the canonical-entity. The method also includes suppressing one or more entities of the identified entities based on the duplication-value of the entity and social-graph information associated with the entity.

Abstract: An attribute correlation system reduces network traffic and processing cycles associated with impromptu item selections by generating attribute preference models based on disparate attribute spectrums. The attribute correlation system deploys the attribute preference models to select individual items from various disparate “candidate item categories.” Generally described, the attribute preference models facilitate analyzing item sets across a wide variety of disparate “candidate” item categories to preemptively identify individual items for a user. In this way, the individual items may be identified and, ultimately, selected for the user even absent any indication that the user has searched for otherwise identified these items or even other items from within the disparate “candidate” item categories. The “candidate” item categories may be determined to be disparate from one another based on a relationship void existing such that predefined relationships are missing between these “candidate” item categories.

Abstract: An adaptive video compression system may receive video data to be compressed, such as for delivery to a user device by a video streaming service. For example the video data may be an entire video file or a segment of a video file. The adaptive video compression system determines a suitable encoding scheme for compressing the video data. In order to determine the encoding scheme, the video data may be analyzed to extract a plurality of features interests of the video data, which may represent one or more characteristics of the video data. The features may be concatenated and collectively expressed as a feature vector. The feature vector is then used to determine a classification for the video data. Accordingly, an encoding scheme is determined for the video data based on the classification of the video data, and applied to video data to compress the video data.

Abstract: Aspects of the disclosure provide for a computer-implemented method. Examples of the method include receiving internal data points from a plurality of sensors associated with a person, the internal data points including at least situational data and biological data, receiving external data points, and comparing the internal data points to the external data points and a profile of the person. The method further includes analyzing the internal data points, the external data points, the profile of the person, and a result of the comparison by applying weighting rules to determine at least one weighted value, where the weighted value is determined according to a first cognitive dimension of an emotional and biological condition of the person and a second cognitive dimension of a situational and contextual condition surrounding the person, comparing the weighted value to a threshold value, and providing an alert when the weighted value exceeds the threshold value.

Abstract: Various embodiments provide for visual similarity based search techniques that certain desirable visual attributes of one or more items to search for items having similar visual attributes. In order to create an electronic catalog of items that is searchable by parts-based visual attributes, the visual attributes are identified and corresponding feature vectors are extracted from the image data of each item. Thus, feature values of parts-based visual attributes of items in the electronic catalog can be determined and used to select or rank the items in response to a search query based on desirable visual attributes. To conduct a search, a user may define desirable visual attributes of one or more items. The feature vectors of the desirable visual attributes are determined and used to query the electronic catalog of items, in which items having visual attributes of similar feature vectors are selected and returned as search results.

Abstract: Provided is an apparatus and method which prioritizes transaction objects included on a reference list. The reference list contains transaction object information corresponding to the transaction objects. The apparatus stores a user's history of actions performed on the transaction objects and an interest parameter based on the user's history of actions. The interest parameter is used to select one or more transaction objects. The apparatus displays the reference list in an order prioritizing the selected transaction objects over non-selected transaction objects.

Abstract: A network crawler crawls one or more media sites to extract a plurality of titles for information contained in the one or more media sites. For example, the network crawler may extract the titles on the one or more media sites by identifying different computer formats and converting the titles in the different computer formats into a common computer format for comparison. User profiles which, includes user's interest are stored in a user profile interest database. A novel personalized news recommendation engine recommends news similar to the interest specified in a user profile, where maximum weighted matching is applied to score the similarity of news against user interest in the word2vec space.