33 results about "Co-occurrence networks" patented technology

Techniques are provided for performing sentiment analysis on words in a first data set. An example embodiment includes generating a word embedding model including a first plurality of features. A value indicating sentiment for the words in the first data set can be determined using a convolutional neural network (CNN). A second plurality of features are generated based on bigrams identified in the data set. The bigrams can be generated using a co-occurrence graph. The model is updated to include the second plurality of features, and sentiment analysis can be performed on a second data set using the updated model.

The invention relates to the technical field of social networks, in particular to a micro-blog hot word and hot topic mining system and method. The method includes the following steps that content data released in a micro-blog are preprocessed to acquire a candidate hot word sequence; according to the frequency of occurrence and suddenness of candidate hot words in a candidate hot word set at the current moment and in a given historical time window, the vitality of each candidate hot word is worked out, and a hot word set is formed by screening the candidate hot words; according to the hot word set formed by screening the candidate hot words, hot word correlation is worked out, and a hot word co-occurrence network is constructed; according to the hot word co-occurrence network, the hot word set is partitioned through the hot word clustering algorithm based on multi-label propagation to acquire a hot topic set. By means of the micro-blog hot word and hot topic mining system and method, efficient micro-blog hot word and hot topic mining is achieved, and mining precision and processing efficiency are improved.

The invention provides a fine-granularity sentiment classification method based on a sentimental word random co-occurrence network. The method comprises the steps of: forming a random network model based on a word sequence and constructed with sentiment characteristics, namely a sentimental word co-occurrence network model, by use of a random network theory and a word co-occurrence phenomenon through annotation of a sentimental noumenon vocabulary library; and carrying out model reduction on the basis, combining a sentimental word longest match (SWLM) method with a TC (Text Category) algorithm to carry out SWLM-TC unsupervised learning classification, or further combining the sentimental word longest match method with an HMM (Hidden Markov Model) machine learning algorithm to establish a fine-granularity sentiment classification model, and realizing classification prediction by use of the model. According to the method, the fine-granularity sentiment classification of a paragraph-level text can be realized, the precision of a pure TC algorithm is improved so that the classification is accurate; and after an HMM model training is carried out on a sample set by use of the SWLM-TC algorithm, the sentiment classification is carried out on a to-be-tested sample database, the automation of a pure machine learning algorithm is improved.

The invention relates to a representation learning-based knowledge base entity classification calculation apparatus, and relates to the field of text classification and knowledge base complementation.The method comprises the steps of for entities in a knowledge base, constructing a co-occurrence network containing information of different levels, and coding co-occurrence information between wordsand words, between the entities and the words, between categories and the words and between the entities and the categories to the network; based on the constructed co-occurrence network, learning vector representation of the entities and the categories by utilizing a network-based representation learning method; based on the learnt vector representation, learning a mapping matrix for the entities and the categories by utilizing a learning sorting algorithm, wherein the semantically related entities and categories are approximate in a semantic space; and by utilizing a top-bottom search method, automatically allocating the categories to the entities in the knowledge base, and obtaining a path of a category. The method is in favor of solving the problem existent in an existing entity classification method.

The invention discloses a method and a device for acquiring knowledge graph vectoring expression. The method comprises the following steps of labeling an entity, existed in and belonging to a knowledge graph, in a given auxiliary text corpus by utilization of an entity labeling tool according to a to-be-processed knowledge graph so as to obtain an entity-labeled text corpus; constructing a co-occurrence network comprising words and entities on the basis of the text corpus so as to relate text information of the auxiliary text corpus to entity information of the knowledge graph, and then learning to obtain a text context embedded expression; respectively modeling the embedded expression of the entity and relation in the knowledge graph according to the text context embedded expression so as to obtain an embedded expression model of the knowledge graph; training the embedded expression model by utilization of a stochastic gradient descent algorithm so as to obtain the embedded expression of the entity and relation in the knowledge graph. The method and the device disclosed by the invention have the advantages that not only can the expression capability of the relation be improved, but also the problem of insufficient expression effect caused by sparseness of the knowledge graph can be effectively solved.

The disclosure provides a document clustering method, including: constructing a word co-occurrence network according to multiple documents to be clustered; calculating the link similarity between any two links connecting the same node in the word co-occurrence network; according to The link similarity extracts a plurality of keyword communities from the word co-occurrence network; according to the document representation vector of each document to be clustered and the community representation vector of each keyword community, each document to be clustered Assign to corresponding keyword communities, and generate initial document clusters corresponding to each keyword community according to the assignment results, wherein all documents to be clustered in the same keyword community constitute an initial document cluster. The present disclosure also provides a document clustering platform, a server and a computer-readable medium.

The invention belongs to the technical field of service computation, and relates to a service and tag recommendation method based on random walk. The method comprises a service recommendation step and a tag recommendation step, wherein the service recommendation step comprises the following process of: collecting the information of a Mashup service and an API (Application Program Interface) service, abstracting the relation between the Mashup service and the API service by association, sorting each tag after performing random walk on a co-occurrence network between the tags, and recommending the Mashup service through the association relation between the tag and the Mashup service and the Mashup semantic expansion method. The tag recommendation method comprises the following process of: searching the nearest neighbor according to the similarity of the API service description texts, and performing tag recommendation of the API service through the random walk and tag sorting method. The recommendation method can be used for improving the accuracy of the service searching result, and solving the problem of tag randomness.

The present application relates to a recommendation method, system and electronic device for learning based on network representation. The method comprises the following steps: step a: constructing auser-article co-occurrence network based on a bipartite graph network and a single projection image; step b: For the user-article co-occurrence network, defining search strategy to get neighbor nodesof each user node and item node. C, according to each user node, article node and respective neighbor node, obtaining vector representation of each user node and article node by using representation learning on network; Step d: according to the vector representation of each user node and the article node, obtaining the most relevant article node of each user node through vector calculation, and recommending the most relevant article to each user according to the calculation result. The present application alleviates the problem of sparsity of collaborative filtering, makes the recommendation system more interpretable, and greatly alleviates the problem of scalability in collaborative filtering.