90 results about "Sentiment score" patented technology

The sentimental significance of a group of historical documents related to a topic is assessed with respect to change in an extrinsic metric for the topic. A unique sentiment binding label is included to the content of actions documents that are determined to have sentimental significance and the group of documents is inserted into a historical document sentiment vector space for the topic. Action areas in the vector space are defined from the locations of action documents and singular sentiment vector may be created that describes the cumulative action area. Newly published documents are sentiment-scored by semantically comparing them to documents in the space and / or to the singular sentiment vector. The sentiment scores for the newly published documents are supplemented by human sentiment assessment of the documents and a sentiment time decay factor is applied to the supplemented sentiment score of each newly published documents. User queries are received and a set of sentiment-ranked documents is returned with the highest age-adjusted sentiment scores.

The sentimental significance of a group of historical documents related to a topic is assessed with respect to change in an extrinsic metric for the topic. A unique sentiment binding label is included to the content of actions documents that are determined to have sentimental significance and the group of documents is inserted into a historical document sentiment vector space for the topic. Action areas in the vector space are defined from the locations of action documents and singular sentiment vector may be created that describes the cumulative action area. Newly published documents are sentiment-scored by semantically comparing them to documents in the space and / or to the singular sentiment vector. The sentiment scores for the newly published documents are supplemented by human sentiment assessment of the documents and a sentiment time decay factor is applied to the supplemented sentiment score of each newly published documents. User queries are received and a set of sentiment-ranked documents is returned with the highest age-adjusted sentiment scores.

Methods for deriving a brand sentiment are presented. Phrases and ratings associated with the brand are stored in a database. The phrases are analyzed and compared to each other and to the ratings to derive a statistical significance of a phrase usage relative to other phrases. A sentiment score is derive from the statistical significance.

Performing detailed sentiment analysis includes generating a first sentiment score for a first entity based on a content source. The first sentiment score is generated with respect to a first dimension. A second sentiment score for the first entity is generated based on the content source. The second sentiment score is generated with respect to a second dimension.

A method and apparatus for prediction of community reaction to a post for an online social community is disclosed. The method comprises receiving a proposed post as input to a generated prediction model prior to the proposed post being posted to an online social community; predicting a community reaction to the proposed post using the prediction model; and displaying the predication, wherein the prediction comprises a sentiment score and at least one of a number of responses, a number of responders to the post, a longevity of the post, or a half-life of the post.

A method for estimating a sentiment conveyed by the content of information sources towards an entity is presented. The sentiment is obtained with respect to a query context that may be specified, e.g. by specific terms or expressions, like a product or service name. A sentiment dictionary having a plurality of sentiment terms is provided, wherein each sentiment term has assigned a sentiment value, and at least one of said sentiment terms is associated to a group context. Text documents are screened for occurrences of sentiment terms that are associated to a group context corresponding to the query context. Calculating a sentiment score value is performed as a function of the occurrences of sentiment terms having a similar or same group context as the query context. The method may be carried out automatically without manual analysis of the actual semantic content of the text documents under consideration.

A domain-specific sentiment classifier that can be used to score the polarity and magnitude of sentiment expressed by domain-specific documents is created. A domain-independent sentiment lexicon is established and a classifier uses the lexicon to score sentiment of domain-specific documents. Sets of high-sentiment documents having positive and negative polarities are identified. The n-grams within the high-sentiment documents are filtered to remove extremely common n-grams. The filtered n-grams are saved as a domain-specific sentiment lexicon and are used as features in a model. The model is trained using a set of training documents which may be manually or automatically labeled as to their overall sentiment to produce sentiment scores for the n-grams in the domain-specific sentiment lexicon. This lexicon is used by the domain-specific sentiment classifier.

A computer-implemented method for product search using the User-Weighted, Attribute-Based, Sort-Ordering comprising the steps of: computing of specification score for product attribute; computing of sentiment score for product attribute; characterized by steps of: —extracting reviews for each product from multiple sources; detecting the attributes described in each product review; detecting the polarity (positive / negative) of the user review with respect to each attribute converting the said attributes into a numerical score for each attribute which captures all the information about that attribute from user-ratings; computing an overall product score using the specifications score and sentiment score for individual product attributes; and displaying the search results sorted according to the overall product score.

Embodiments generally relate to systems and methods for generating a sentiment dictionary and calculating sentiment scores of adjectives within the sentiment dictionary. A set of seed words can be identified and expanded using synonyms and antonyms of the set of seed words. Social media data can be parse to identify adjectives that link to the set of seed words with the words “and” or “but.” Matrices representing the attraction and repulsion among the linked adjectives can be generated. A factorization algorithm can be minimized to determine an output matrix that comprises positive and negative sentiment scores for each of the adjectives. In embodiments, a sentiment score for part of all of the social media data can be calculated using the output matrix, and one or more parts of the social media data can be classified as a positive or negative sentiment.

A method for estimating a sentiment conveyed by the content of information sources towards an entity is presented. The sentiment is obtained with respect to a query context that may be specified, e. g. by specific terms or expressions, like a product or service name. A sentiment dictionary having a plurality of sentiment terms is provided, wherein each sentiment term has assigned a sentiment value, and at least one of said sentiment terms is associated to a group context. Text documents are screened for occurrences of sentiment terms that are associated to a group context corresponding to the query context. Calculating a sentiment score value is performed as a function of the occurrences of sentiment terms having a similar or same group context as the query context. The method may be carried out automatically without manual analysis of the actual semantic content of the text documents under consideration.

The invention relates to an image evaluation algorithm based on microblog sentiment analysis. The algorithm includes the following steps that microblog client information is collected; secondly, relative microblog keyword database is constructed; thirdly, a microblog sentiment score is calculated, and microblog comment sentiment tendency types are judged; fourthly, microblog comment types are divided and related and matched with enterprise service events; fifthly, an image core is calculated. Microblog comments, related to a power grid, of users serve as research objects, the method combining the text mining technology and sentiment analysis is adopted, the enterprise image scorning algorithm based on microblog sentiment analysis is built, and a strong technical means is provided for power supply enterprises to judge images and take pertinent measures.

An approach is provided to use natural language processing (NLP) to analyze data logs. In the approach, a data log is analyzed with the data log including a number of entries. The analysis performed includes performance of a sentiment analysis of the entries using natural language processing. The result of the sentiment analysis results is a sentiment score. Entries from the data log are then visually highlighted based on their corresponding sentiment scores.

The present invention provides a system and method for customer evaluation and retention. The system is adapted to receive and record all data concerning customer's interaction during the transaction from various touch points and sends the data to a server for further processing. The scoring module of the system allocates values to each customer by assigning score based on various scoring attributes. The final updated information about each customer is pushed back to all touch points that will be further used by business owners for formulating customer retention programs. The availability of real time information regarding customer net present value is beneficial in computing and proposing retention program as the evaluation data is based on past trends taking into consideration recency, frequency, monetary history and individual sentiment scores.

A method including identifying an emotion identifier from a message using an emotion identifier table is provided. The method includes separating emotion identifier from the message, splitting a portion into multiple tokens delimited by a space or a punctuation mark, and determining a score for the message based on an emotion score in the emotion identifier table, and on at least one of the multiple tokens. The method includes adding a token from the multiple tokens to the emotion identifier table based on a contribution from the token to the message score, associating a sentiment score for the token in the emotion identifier table based on the contribution of the token to the message score, and modifying an emotion score of the token when the token is already included in the emotion identifier table based on the contribution of the token to the message sentiment score.

Embodiments generally relate to systems and methods for generating a sentiment dictionary and calculating sentiment scores of adjectives within the sentiment dictionary. A set of seed words can be identified and expanded using synonyms and antonyms of the set of seed words. Social media data can be parse to identify adjectives that link to the set of seed words with the words “and” or “but.” Matrices representing the attraction and repulsion among the linked adjectives can be generated. A factorization algorithm can be minimized to determine an output matrix that comprises positive and negative sentiment scores for each of the adjectives. In embodiments, a sentiment score for part of all of the social media data can be calculated using the output matrix, and one or more parts of the social media data can be classified as a positive or negative sentiment.

The disclosed embodiments provide a system for facilitating sentiment analysis. During operation, the system obtains a set of training data that includes a first set of content items containing words associated with a domain, a set of sentiment scores for the first set of content items, and a set of outcomes associated with the first set of content items. Next, the system uses the training data to train a statistical model for performing sentiment analysis that is specific to the domain. The system then enables use of the statistical model in generating a set of domain-specific sentiment scores for a second set of content items containing words associated with the domain.

Certain aspects of the present disclosure provide techniques for generating a replacement sentence with the same or similar meaning but a different sentiment than an input sentence. The method generally includes receiving a request for a replacement sentence and iteratively determining a next word of the replacement sentence word-by-word based on an input sentence. Iteratively determining the next word generally includes evaluating a set of words of the input sentence using a language model configured to output candidate sentences and evaluating the candidate sentences using a sentiment model configured to output sentiment scores for the candidates sentences. Iteratively determining the next word further includes calculating convex combinations for the candidate sentences and selecting an ending word of one of the candidate sentences as the next word of the replacement sentence. The method further includes transmitting the replacement sentence in response to the request for the replacement sentence.

Certain aspects of the present disclosure provide techniques for displaying sentiment of a user text comment. One example method generally includes receiving a text comment comprising a sequence of words, providing a vector sequence representing the sequence of words to a sentiment model configured to output a sequence of sentiment scores for the vector sequence and providing cleaned text to a topic module configured to output relevance scores. The method further includes receiving, from the sentiment model, the sequence of sentiment scores for the vector sequence and receiving, from the topic module, the relevance scores for the cleaned text. The method further includes determining, final sentiment scores for each word of the sequence of words and generating a sentiment visualization for the sequence of words showing the final sentiment scores corresponding to each word of the sequence of words.

A content evaluation system is described herein that empowers end users and organizations to share their interpretation of an automatically generated sentiment score. The system provides a control that a user can move to indicate agreement or disagreement with an automatic score. The system adds metadata to a revised score based on the user's feedback that tracks information about the user to consider different demographic contexts. The system performs rescoring with the user-provided scores with contextual consideration, and then exposes the rescored values on context specific endpoints. The system provides a crowd-sourcing approach that scales extremely well, adds more accuracy because individuals within known demographic categories / contexts do the scoring, and generates value-added data products that can be sold / re-sold.

A method, a system and a computer program product for ranking reviewable entities based on sentiment expressed about the entities. A plurality of review texts are identified wherein each review text references an entity. A plurality of sentiment scores associated with the plurality of review texts are generated, wherein each sentiment score for a review text indicates a sentiment directed to the entity referenced by the review text. A plurality of ranking scores for the plurality of entities are generated wherein each ranking score is based at least in part on one or more sentiment scores associated with one or more review texts referencing the entity. A plurality of search results associated with the plurality of entities are displayed based at least in part on the ranking scores.

In one exemplary embodiment, a method includes the step of obtaining a digital image of a user with a user-facing camera of a computing device. It is determined that the digital image includes a frontal image of the user. A user-sentiment score is calculated based on at least one attribute of the frontal image. A user engagement value is determined with respect to a portion of a display of the computing device. At least one of the frontal image of the user, the user-sentiment score or the gaze position of the user is communicated to an external server process or an application operating in the computing device.

A method and apparatus for prediction of community reaction to a post for an online social community is disclosed. The method comprises receiving a proposed post as input to a generated prediction model prior to the proposed post being posted to an online social community; predicting a community reaction to the proposed post using the prediction model; and displaying the predication, wherein the prediction comprises a sentiment score and at least one of a number of responses, a number of responders to the post, a longevity of the post, or a half-life of the post.

A method for classifying information sources and content based on credibility, reliability, or trust. A content item describing an event is retrieved from an information provider and parsed for links. Each link is evaluated and attributed a sentiment score. The same event is identified in a set of know sources and an event score is calculated based on the credibility of each of the known sources. Finally, the content item is ranked based on the event and sentiment scores.

Systems, devices, and methods for automating network account transfers based on predicted inactivity are disclosed. In one embodiment, the system comprises a mail server providing access to an email account of a user; a social graph monitor configured to: periodically query, over a network, a social graph associated with the user to retrieve at least one social network feed associated with the user, calculate a sentiment score for the social network feed based on parsing the social network feed using a natural language parser, and determining that a transfer condition has occurred if the sentiment score exceeds a pre-defined sentiment score threshold; and a condition processor configured to: transmit, via the mail server, a password reset request to a network application associated with the transfer condition, intercept an email from the network application, via the mail server, transmitted in response to the password reset request, forward, via the mail server, the email to a recipient associated with the transfer condition, determine that the recipient has reset a password associated with the network application, and forward, to the recipient via the mail server, subsequent emails from the network application.

The invention discloses a short text sentiment analysis method based on a CNN (Convolutional Neural Network) bidirectional GRU attention mechanism. The method comprises the following steps: preprocessing a short text, denoising, segmenting words, labeling part of voice, and removing stop words; expressing sentences into a word sequence through negative sampling training by taking words as units through a continuous bag-of-words model (CBOW), and mapping the word sequence into a multi-dimensional vector to construct a word vector set; calculating the occurrence frequency of sentiment words in different data set documents, calculating sentiment scores, and converting the sentiment scores into a sentiment feature vector matrix; word embedding and feature embedding topology serves as input ofa convolutional neural network, and sentence representation is obtained through convolution and pooling; through a bidirectional GRU recurrent neural network, negative word turning words are set as parameter query items of an attention mechanism to obtain representation; and combining the two representation topologies to serve as full connection layer input, and outputting an emotion analysis result.

One embodiment provides a method, including: accessing, for an identified individual, a sentiment profile comprising at least one average sentiment score, wherein the sentiment profile is generated by analyzing interactions of the identified individual with other individuals and wherein the sentiment profile reflects the identified individual's personality in interactions with other individuals; receiving input corresponding to a current interaction between the identified individual and at least one other individual; generating a current sentiment score for the identified individual corresponding to the current interaction using a sentiment analysis tool; determining a sentiment intent of the identified individual corresponding to the current interaction, wherein the determining a sentiment intent comprises comparing the current sentiment score to the at least one average sentiment score from the sentiment profile; and providing to a user, feedback of the determined sentiment intent of the identified individual.

An approach is provided that analyzes electronic document sets, each of the sets written by a different author. The analysis includes performing a normalized sentiment analysis of the documents which results in normalized sentiment scores that pertain to each of the authors. The normalize sentiment scores are stored in a data store that is accessible from a question answering (QA) system. The question answering system then receives a sentiment-based question. Responsively, the QA system generates a qualitative set of candidate answers, with the candidate answers based at least in part on the normalized sentiment scores retrieved from the data store.

Techniques are disclosed for improved autonomous agents that can provide a recommendation in a non-intrusive, conversational manner. In an aspect, a method determines a first sentiment score for a first utterance and a second sentiment score for a second utterance, each sentiment score indicating an emotion indicated by the respective utterance. The method further identifies that a difference between the first sentiment score and the second sentiment score is greater than a threshold. The method further extracts a noun phrase from the second utterance. The method identifies a text fragment that includes an entity that corresponds to the noun phrase. The method identifies that the text fragment addresses a claim of the second utterance. The method forms a third utterance that includes the a recommendation related to the second utterance and adds the third utterance to the sequence of utterances after the second utterance.

Systems and methods are provided for displaying received publishing content on a web page along with one or more user elements by which one or more users may submit sentiment input or textual input in relation to the received publishing content or a subportion of the received publishing content; receiving a user input related to the displayed publishing content displayed on the web page, the user input including an identification of a subportion of the displayed publishing content and a sentiment input or a textual input; analyzing any user input received from each of one or more of the plurality of users in relation to the subportion; computing a sentiment score based on analysis of the analyzed user inputs received from each of one or more of the plurality of users in relation to the subportion; and displaying indicia representing the sentiment score computed for the subportion.

The invention discloses a text sentiment analysis method and device, a computer device and a computer readable storage medium. The method comprises the following steps: extracting a plurality of target articles from a preset corpus by utilizing a preset extraction rule; carrying out sentiment classification on the statement of each target article by utilizing a pre-established sentiment word segmentation dictionary; according to the sentiment classification result of the sentiment, carrying out sentiment scoring on the sentiment of each target article; obtaining an emotion classification result of each target article based on the emotion scoring condition of the statement in each target article; processing each target article in a preset mode to obtain text data after word segmentation; obtaining training data with emotion classification labels according to the text data of each target article and the emotion classification result of each target article, and obtaining an emotion classification model through training based on the training data; and performing sentiment classification on a to-be-processed article by utilizing the sentiment classification model. Article emotion can beaccurately analyzed and classified.