A time-aware query-focused summarization of an evolving microblogging stream via sentence extraction

With the number of social media users ramping up,microblogs are generated and shared at record levels.The high momentum and large volumes of short texts bring redundancies and noises,in which the users and analysts often find it problematic to elicit useful information of interest.In this paper,we study a query-focused summarization as a solution to address this issue and propose a novel summarization framework to generate personalized online summaries and historical summaries of arbitrary time durations.Our framework can deal with dynamic,perpetual,and large-scale microblogging streams.Specifically,we propose an online microblogging stream clustering algorithm to cluster microblogs and maintain distilled statistics called Microblog Cluster Vectors(MCV).Then we develop a ranking method to extract the most representative sentences relative to the query from the MCVs and generate a query-focused summary of arbitrary time durations.Our experiments on large-scale real microblogs demonstrate the efficiency and effectiveness of our approach.

Study on Multi-Label Classification of Medical Dispute Documents

The Internet of Medical Things(IoMT)will come to be of great importance in the mediation of medical disputes,as it is emerging as the core of intelligent medical treatment.First,IoMT can track the entire medical treatment process in order to provide detailed trace data in medical dispute resolution.Second,IoMT can infiltrate the ongoing treatment and provide timely intelligent decision support to medical staff.This information includes recommendation of similar historical cases,guidance for medical treatment,alerting of hired dispute profiteers etc.The multi-label classification of medical dispute documents(MDDs)plays an important role as a front-end process for intelligent decision support,especially in the recommendation of similar historical cases.However,MDDs usually appear as long texts containing a large amount of redundant information,and there is a serious distribution imbalance in the dataset,which directly leads to weaker classification performance.Accordingly,in this paper,a multi-label classification method based on key sentence extraction is proposed for MDDs.The method is divided into two parts.First,the attention-based hierarchical bi-directional long short-term memory(BiLSTM)model is used to extract key sentences from documents;second,random comprehensive sampling Bagging(RCS-Bagging),which is an ensemble multi-label classification model,is employed to classify MDDs based on key sentence sets.The use of this approach greatly improves the classification performance.Experiments show that the performance of the two models proposed in this paper is remarkably better than that of the baseline methods.

CitationAS： A Tool of Automatic Survey Generation Based on Citation Content

Purpose： This study aims to build an automatic survey generation tool, named CitationAS, based on citation content as represented by the set of citing sentences in the original articles.Design/methodology/approach： Firstly, we apply LDA to analyse topic distribution of citation content. Secondly, in CitationAS, we use bisecting K-means, Lingo and STC to cluster retrieved citation content. Then Word2Vec, Word Net and combination of them are applied to generate cluster labels. Next, we employ TF-IDF, MMR, as well as considering sentence location information, to extract important sentences, which are used to generate surveys. Finally, we adopt manual evaluation for the generated surveys.Findings： In experiments, we choose 20 high-frequency phrases as search terms. Results show that Lingo-Word2Vec, STC-Word Net and bisecting K-means-Word2Vec have better clustering effects. In 5 points evaluation system, survey quality scores obtained by designing methods are close to 3, indicating surveys are within acceptable limits. When considering sentence location information, survey quality will be improved. Combination of Lingo, Word2Vec, TF-IDF or MMR can acquire higher survey quality.Research limitations： The manual evaluation method may have a certain subjectivity. We use a simple linear function to combine Word2Vec and Word Net that may not bring out their strengths. The generated surveys may not contain some newly created knowledge of some articles which may concentrate on sentences with no citing.Practical implications： CitationAS tool can automatically generate a comprehensive, detailed and accurate survey according to user’s search terms. It can also help researchers learn about research status in a certain field.Originality/value： Citaiton AS tool is of practicability. It merges cluster labels from semantic level to improve clustering results. The tool also considers sentence location information when calculating sentence score by TF-IDF and MMR.