&

人工智能研究院

服務(wù)國家的人工智能戰(zhàn)略科技力量

核心技術(shù)

深度語義理解

Deep Semantic Understanding
社會(huì)計(jì)算

Social Computing
人工智能工程

AI Engineering

學(xué)術(shù)前沿

Extracting Impacts of Non-pharmacological Interventions for COVID-19 From Modelling Study

COVID-19 pandemic continues to rampage in the world. Before the achievement of global herd immunity,non-pharmacological interventions(NPIs) are crucial to mitigate the pandemic. Although various NPIs have been put into practice, there are many concerns about the impacts and effectiveness of these NPIs. COVID-19 modelling study (CMS) in epidemiology can provide evidence to solve the aforementioned concerns. It is time-consuming to collect evidence manually when dealing with the vast amount of CMS papers. Accordingly, we seek to accelerate evidence collection by developing an information extraction model to automatically identify evidence from CMS papers. This work presents a novel COVID-19 Non-pharmacological Interventions Evidence (CNPIE) Corpus, which contains 597 abstracts of COVID-19 modelling study with richly annotated entities and relations of the impacts of NPIs. We design a semi-supervised document-level information extraction model (SS-DYGIE++) which can jointly extract entities and relations. Our model outperforms previous baselines in both entity recognition and relation extraction tasks by a large margin. The proposed work can be applied towards automatic evidence extraction in the public health domain for assisting the public health decision-making of the government.

Identifying Risks of the Internet Finance Platforms Using Multi-Source Text Data

With the explosion of the Internet Finance Platforms, identifying the risks of these platforms is of growing significance, which can help discover problematic platforms in time and ensure the healthy development of the Internet finance industry. In this paper, we design a risk index system to measure the quantitative risk of the Internet finance platforms, and propose a deep neural network based model, CBiGRU-RI, to identify the risks of the platforms using multi-source text data. We conducted comparative experiments with various baseline models on real-world data. The experimental results show that our proposed model can identify the risks of platforms more effectively than the baseline methods.

A Framework for Policy Information Popularity Prediction in New Media

With the rapid development and wide application of new media, predicting the popularity of policyinformation on new media is of great significance for understanding and managing public opinion. However, the complexity of the diffusion patterns of policy information has brought great challenges for predicting the popularity of such information. Inspired by the methods of popularity prediction for short text information from social networks, we propose a framework for the popularity prediction of policy information. In our framework, first, the features of policy information are extracted from three dimensions: contextual information, social information and textual information. Then, effective features, such as the topic distribution, popularity competition intensity and hot information relevance, are identified by empirical analysis. Finally, the effective features are input into the prediction model to predict the popularity of policy information. We evaluate the performance of our proposed framework using a real-world dataset and the experimental results show that the framework can efficiently predict the popularity of policy information and that the features that we used are effective in improving the accuracy of policy information popularity prediction. The accurate prediction result could benefit policy makers, allowing them to make better decisions, understand and manage public opinion.

Adaptively temporal graph convolution model for epidemic prediction of multiple age groups

Multivariate time series prediction of infectious diseases is significant to public health, and the deep learning method has attracted increasing attention in this research field.

Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study

The needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of science. Tremendous unstructured COVID-19 publications make it challenging for policymakers to obtain relevant evidence. Knowledge graphs (KGs) can formalize unstructured knowledge into structured form and have been used in supporting decision-making recently. Here, we introduce a novel framework that can extract the COVID-19 public health evidence knowledge graph (CPHE-KG) from papers relating to a modelling study. We screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment process. We define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset (CPHIE). We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++ based on the dataset. Leveraging the model on the new corpus, we construct CPHE-KG containing 60,967 entities and 51,140 relations. Finally, we seek to apply our KG to support evidence querying and evidence mapping visualization. Our
SS-DYGIE++(SpanBERT) model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution tasks. It has also shown high performance in the relation identification task. With evidence querying, our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and regions. The evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 pandemic. Analysis demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.

A Central Opinion Extraction Framework for Boosting Performance on Sentiment Analysis

With the rapid development of the Internet, mining opinions and emotions from the explosive growth of user generated content is a key field of social media analysis. However, the expression forms of the central opinion which strongly expresses the essential points and converges the main sentiments of the overall document are diverse in practice, such as sequential sentences, a sentence fragment, or an individual sentence. Previous research studies on sentiment analysis based on document level and sentence level fail to deal with this actual situation uniformly. To address this issue, we propose a Central Opinion Extraction (COE) framework to boost performance on sentiment analysis with social media texts. Our framework first extracts a span-level central opinion text, which expresses the essential opinion related to sentiment representation among the whole text, and then uses extracted textual span to boost the performance of sentiment classifiers. The experimental results on a public dataset show the effectiveness of our framework for boosting the performance on document-level sentiment analysis task.

A Deep Learning Approach for Semantic Analysis of COVID-19-Related Stigma on Social Media

The rapid spread of the pandemic of coronavirus disease of 2019 (COVID-19) has created an unprecedented, global health disaster. During the outburst period, the paucity o... View more

基于高斯混合模型的無線傳感器網(wǎng)絡(luò)定位算法

針對(duì)距離誤差對(duì)定位結(jié)果的影響,提出一種基于高斯混合模型的無線傳感器網(wǎng)絡(luò)定位算法.該算法將高斯混合模型方法引入到無線傳感器網(wǎng)絡(luò)的定位問題中,通過高斯混合模型分析找出誤差較大的距離信息并將其剔除,對(duì)剩余距離信息使用三邊測(cè)量定位法進(jìn)行定位求解,同時(shí)結(jié)合加權(quán)定位算法進(jìn)行位置估計(jì).仿真實(shí)驗(yàn)結(jié)果表明,改進(jìn)算法能提高定位精度,且定位結(jié)果更穩(wěn)定。

Integrating Deep Learning Approaches for Identifying News Reprint Relation

With the rapid development of big data and new media technologies, a large amount of original news is generated and reprinted on the Internet via news portals. Identifying news reprint relations is of great importance for the analysis of news diffusion patterns and copyright protection. However, the amount of news data on the Internet creates a huge challenge for efficiently identifying news reprint relation. Some existing studies focus on computing the similarity of the full text of news reports, which is not always effective, because some reprints only excerpt some sentences of the original news reports. The core challenge of improving identification accuracy is excavating the potential semantic relevance between news articles at the sentence level. Inspired by deep learning and semantic-based text representation models, this paper proposes an approach for identifying news reprint relation by integrating deep learning approaches. First, news reports that are not related to the topic of the original news report are removed via topic correlation mining. Then, the potential semantic relevance is excavated at the sentence level through the integration of semantic analysis methods, and reprint relations are identified between news reports. The performance of the approach is empirically evaluated using a real-world dataset. Experimental results show that the semantic analysis model integration allows us to mine in-depth semantic associations between news stories and accurately identify news reprint relations. These results benefit news diffusion pattern analysis and copyright protection.

Exploring Trends and Patterns of Popularity Stage Evolution in Social Media

以往針對(duì)互聯(lián)網(wǎng)事件傳播分析和預(yù)測(cè)工作中往往只對(duì)其發(fā)展趨勢(shì)進(jìn)行刻畫，而缺少在更細(xì)粒度上對(duì)其發(fā)展演化階段的建?：馱げ?。本研究工作綜合考慮了參與用戶和事件自身在內(nèi)容、結(jié)構(gòu)和關(guān)聯(lián)關(guān)系等多方面的動(dòng)態(tài)影響因素，并同時(shí)挖掘其演化模式信息，提出一種融合動(dòng)態(tài)因素和演化模式的事件發(fā)展階段預(yù)測(cè)方法。

了解更多 >>