Titlebook: Social Media Processing; 4th National Confere Xichun Zhang,Maosong Sun,Xuanjing Huang Conference proceedings 2015 Springer Science+Business

共栖

煞费苦心

Predicting User Relationship from Scratch,sers is often tantamount to the reliability of the information they provide. In this paper we focus on automatic methods for assessing the credibility of a given pair of users. Specifically, we establish a model to classify them as credible or not credible, based on features extracted from them. We

facetious

Detecting Overlapping and Hierarchical Communities in Complex Network Based on Maximal Cliques,er proposes an efficient algorithm OMC for detecting communities based on maximal cliques. Subordinate maximal cliques are removed and remaining cliques are regarded as initial communities. Then small communities are merged into larger ones according to a fitness function. The proposed algorithm is

调色板

The Expert Ranking Method Based on Listwise with Associated Features,tionship and the relative relationship of the expert list. First, construct a correlation model of query and expert by evidence documents, expert display and implicit relationships and expert metadata. Then sort experts by the ListNet algorithm based on the list. Finally perform an experiment under

GEON

Generating Triples Based on Dependency Parsing for Contradiction Detection,tions of the same event is common and harmful. It is urgent to detect contradictory texts. Previous methods on detecting contradiction are mostly deriving features from shallow semantic representations like predicate-argument structures. They meet a problem of the low coverage of contradiction. We p

Pudendal-Nerve

Detecting Overlapping and Hierarchical Communities in Complex Network Based on Maximal Cliques,es are regarded as initial communities. Then small communities are merged into larger ones according to a fitness function. The proposed algorithm is able to uncover both overlapping and hierarchical communities in high speed. Experimental results on various real-word networks have proven that the method performed well in detecting communities.

手势

1865-0929 d from 105 submissions. The papers address issues such as: mining social media and applications; natural language processing; data mining; information retrieval; emergent social media processing problems.978-981-10-0079-9978-981-10-0080-5Series ISSN 1865-0929 Series E-ISSN 1865-0937

CLAMP

A Gaussian Copula Regression Model for Movie Box-office Revenue Prediction with Social Media,week revenue prediction task and can achieve comparable performance on the gross revenue prediction task with a state-of-the art baseline in gross revenue prediction task. Our model is robust under various experimental settings.

修正案

Do Photos Help Express Our Feelings: Incorporating Multimodal Features into Microblog Sentiment Anag environment, we propose a unified model to extract the features of text and image together. Learning based approaches are then adopted to finish sentiment analysis tasks such as subjectivity classification. Experimental results based on practical microblog data show that features extracted from images help gain better sentiment analysis results.

Ebct207