Hot event detection method for social network based on multiple data stream calculation

Abstract

The invention discloses a hot event detection method for social network based on multiple data stream calculation. The hot event detection method comprises the following steps: extracting word features of short text data of user-generated content and making a subject analysis of the word features; establishing differentiations between themes and cohesion within themes and taking sudden themes as features of the user-generated content; establishing self-adaptive unsupervised target decisions with a fuzzy set theory; granulating data of each single data stream and measuring importance and relevance of a multi-granularity structure of multiple data streams in order to reduce and determine relevance of multiple granular structures; and making a coverage analysis of different granule structuresaccording to relevance and target decisions in order to establish calculation of a multi-granularity space and detect hot events. With the hot event detection method, unsupervised and self-adaptive decisions can be made. Multi-source heterogeneous data can be calculated. Hot events in social network can be effectively detected.

Description

technical field

[0001] The invention relates to the fields of natural language processing and text mining, in particular to a method for detecting social network hotspot events based on multi-data stream calculation. Background technique

[0002] Hotspot events have the characteristics of "widespread concern", "uncertainty" and "hazardousness", and have far-reaching impacts. Hot event detection in social networks is particularly important. Hot event detection is not only the theoretical support and challenge of topic detection, public opinion analysis, sentiment analysis, etc., but also the core content of important applications such as social network analysis, network public opinion monitoring, e-commerce platform business analysis, and financial information analysis. For example, in social network analysis, by analyzing the social network communication situation, user behavior, etc., to analyze public sentiment and user influence, and to identify opinion leaders and seed ...

Examples

Embodiment

[0075] Such as figure 1 and figure 2 As shown, a social network hotspot event detection method based on multi-data stream computing includes the following steps:

[0076] S1. Use the deep learning method for processing time series data to extract word features from user-generated content short text data, and perform topic analysis on short text word features;

[0077] Described deep learning method is Long Short-Term Memory (LSTM), for keeping the sequentiality of word in short text, adopts LSTM to extract global word feature;

[0078] The user-generated content short text word feature F is divided into a global word feature and a local word feature, and its expression is: Among them, g i Is the global word feature, G is the global word feature vector; ne j is a named entity, NE is a named entity vector;

[0079] The topic analysis refers to using the document topic generation model LatentDirichlet Allocation (LDA) to identify the topic information hidden in the short t...

technical field

[0001] The invention relates to the fields of natural language processing and text mining, in particular to a method for detecting social network hotspot events based on multi-data stream calculation. Background technique

[0002] Hotspot events have the characteristics of "widespread concern", "uncertainty" and "hazardousness", and have far-reaching impacts. Hot event detection in social networks is particularly important. Hot event detection is not only the theoretical support and challenge of topic detection, public opinion analysis, sentiment analysis, etc., but also the core content of important applications such as social network analysis, network public opinion monitoring, e-commerce platform business analysis, and financial information analysis. For example, in social network analysis, by analyzing the social network communication situation, user behavior, etc., to analyze public sentiment and user influence, and to identify opinion leaders and seed ...

Examples

Embodiment

[0075] Such as figure 1 and figure 2 As shown, a social network hotspot event detection method based on multi-data stream computing includes the following steps:

[0076] S1. Use the deep learning method for processing time series data to extract word features from user-generated content short text data, and perform topic analysis on short text word features;

[0077] Described deep learning method is Long Short-Term Memory (LSTM), for keeping the sequentiality of word in short text, adopts LSTM to extract global word feature;

[0078] The user-generated content short text word feature F is divided into a global word feature and a local word feature, and its expression is: Among them, g i Is the global word feature, G is the global word feature vector; ne j is a named entity, NE is a named entity vector;

[0079] The topic analysis refers to using the document topic generation model LatentDirichlet Allocation (LDA) to identify the topic information hidden in the short t...

Images