Abstract
With the development and popularization of social networks, many users and authoritative media broach and share topics through social networks every day. This type of sharing is widespread and is sometimes the first communication of topics of public discussion. Therefore, research on identifying public opinion topics on social networks is of great significance. However, social network posts are short, sparse and noisy, which creates challenges for this research. To overcome these challenges, we propose a spatial-temporal emergency topic model (ST-ETM) to identify public opinion topics in social networks. By introducing spatial-temporal features into the topic model to construct spatial-temporal regions for focusing on topics, the ST-ETM can alleviate the sparsity problem of context in social networks and succeed in focusing on public opinion topics. Moreover, to automatically identify public opinion topics, we introduce the burstiness of the words as a priori in the model, and binary switch variables are combined to automatically identify public opinion topics in social networks. Based on a real Sina Weibo dataset, several comparative experiments are designed to evaluate the performance of our ST-ETM. The experimental results verify the effectiveness of the proposed ST-ETM method.
Highlights
As an important tool for people to share ideas and spread information, social networks are one of the important data sources in the era of big data
To overcome the above problems, we propose the public opinion topic identification method based on a spatial-temporal emergency topic model, named the ST-ETM, in social networks
The proposed ST-ETM is compared with the comparison algorithm in terms of the accuracy of topic identification, topic coherence, clustering purity, and entropy
Summary
As an important tool for people to share ideas and spread information, social networks are one of the important data sources in the era of big data. The above methods only alleviate the sparsity problem of context in social networks and require tedious postprocessing steps to identify public opinion topics, and the results are still unsatisfactory. To overcome the above problems, we propose the public opinion topic identification method based on a spatial-temporal emergency topic model, named the ST-ETM, in social networks. The ST-ETM introduces the temporal and spatial information of social networks to construct temporal and spatial regions and aggregate short texts as long documents to alleviate the sparsity problem of context in social networks. The main contributions of this paper are as follows: 1) We propose a novel spatial-temporal emergency topic model (ST-ETM) This model can generate more accurate semantic information on social network texts and automatically identify public opinion topics without any postprocessing.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
