Search

With the application of electronic medical records in medical field, more and more people are paying attention to how to use these data efficiently. In this paper, the BiLSTM-CRF model is applied to Chinese electronic medical records to recognize related named entities in these records. For the characteristics of Chinese electronic medical records, firstly, the one-hot vector of each word is obtained in units of sentences. Secondly, map one-hot vector to a low-dimensional dense word vector. Thirdly, word vector is used as the input of the BiLSTM layer to achieve automatic extraction of sentence features. Finally, the CRF layer performs sequence-level labeling of sentences. In addition, drug dictionary and post-correction rules are added to correct the segmentation error of entity boundary, to improve recognition accuracy of related named entities. The F1 value of this method on a given test data set is 87.68%.

Dataset interlinking is a great important problem in Linked Data. We consider this problem from the perspective of information retrieval in this paper, thus propose a learning to rank based framework, which combines various similarity measures to retrieve the relevant datasets for a given dataset. Specifically, inspired by the idea of collaborative filtering, an effective similarity measure called collaborative similarity is proposed. Experimental results show that the collaborative similarity measure is effective for dataset interlinking, and the learning to rank based framework can significantly increase the performance.

An important aspect of communication in Twitter (and other Social Network is message propagation -- people creating posts for others to share. Although there has been work on modelling how tweets in Twitter are propagated (retweeted), an untackled problem has been who will retweet a message. Here we consider the task of finding who will retweet a message posted on Twitter. Within a learning to-rank framework, we explore a wide range of features, such as retweet history, followers status, followers active time and followers interests. We find that followers who retweeted or mentioned the author's tweets frequently before and have common interests are more likely to be retweeters.

In this paper we investigate information propagation in Twitter from the geographical view on the global scale. An information propagation phenomenon what we call "information current" has been discovered. According to this phenomenon, we propose a hypothesis that changes of information flows may be related to real-time events. Through analysis of retweets, we show that our hypothesis is supported by experiment results. Moreover, it is discovered that the retweet texts are more effective than common tweet texts for real-time event detection. This means that Twitter could be a good filter of texts for event detection.

The key issue of person name disambiguation is to discover different namesakes in massive web documents rather than simply cluster documents by using textual features. In this paper, we describe a novel person name disambiguation method based on social networks to effectively identify namesakes. The social network snippets in each document are extracted. Then, the namesakes are identified via splicing the social networks of each namesake by using the snippets as a bipartite graph. Experimental results show that our method achieves better result than the top performance of WePS-2 in identifying different namesakes.

Applying graph clustering algorithms in real world networks needs to overcome two main challenges: the lack of prior knowledge and the scalability issue. This paper proposes a novel method based on the topological features of complex networks to optimize the clustering algorithms in real-world networks. More specifically, the features are used for parameter estimation and performance optimization. The proposed method is evaluated on real-world networks extracted from the web. Experimental results show improvement both in terms of Adjusted Rand index values as well as runtime efficiency.

As a typical social media in Web 2.0, blogs have attracted a surge of researches. Unlike the traditional studies, the social networks mined from Internet are very large, which makes a lot of social network analyzing algorithms to be intractable. According to this phenomenon, this paper addresses the novel problem of efficient social networks analyzing on blogs. This paper turns to account the structural characteristics of real large-scale complex networks, and proposes a novel shortest path approximate algorithm to calculate the distance and shortest path between nodes efficiently. The approximate algorithm then is incorporated with social network analysis algorithms and measurements for large-scale social networks analysis. We illustrate the advantages of the approximate analysis through the centrality measurements and community mining algorithms. The experiments demonstrate the effectiveness of the proposed algorithms on blogs, which indicates the necessity of taking account of the structural characteristics of complex networks when optimizing the analysis algorithms on large-scale social networks.