We propose a novel multi-grained attention network (MGAN) model for aspect level sentiment classification.Existing approaches mostly adopt coarse-grained attention mechanism, which may bring information loss if the aspect has multiple words or larger context.We propose a fine-grained attention mechanism, which can capture the word-level interaction between aspect and context.And then we leverage the fine-grained and coarsegrained attention mechanisms to compose the MGAN framework.Moreover, unlike previous works which train each aspect with its context separately, we design an aspect alignment loss to depict the aspect-level interactions among the aspects that have the same context.We evaluate the proposed approach on three datasets: laptop and restaurant are from SemEval 2014, and the last one is a twitter dataset.Experimental results show that the multi-grained attention network consistently outperforms the state-of-the-art methods on all three datasets.We also conduct experiments to evaluate the effectiveness of aspect alignment loss, which indicates the aspect-level interactions can bring extra useful information and further improve the performance.

This article studies the problem of learning effective representations for Location-Based Social Networks (LBSN), which is useful in many tasks such as location recommendation and link prediction. Existing network embedding methods mainly focus on capturing topology patterns reflected in social connections, while check-in sequences, the most important data type in LBSNs, are not directly modeled by these models. In this article, we propose a representation learning method for LBSNs called as JRLM++, which models check-in sequences together with social connections. To capture sequential relatedness, JRLM++ characterizes two levels of sequential contexts, namely fine-grained and coarse-grained contexts. We present a learning algorithm tailored to the hierarchical architecture of the proposed model. We conduct extensive experiments on two important applications using real-world datasets. The experimental results demonstrate the superiority of our model. The proposed model can generate effective representations for both users and locations in the same embedding space, which can be further utilized to improve multiple LBSN tasks.

The task of tweet timeline generation (TTG) aims at selecting a small set of representative tweets to generate a meaningful timeline and providing enough coverage for a given topical query. This paper presents an approach based on determinantal point processes (DPPs) by jointly modeling the topical relevance of each selected tweet and overall selectional diversity. Aiming at better treatment for balancing relevance and diversity, we introduce two novel strategies, namely spectral rescaling and topical prior. Extensive experiments on the public TREC 2014 dataset demonstrate that our proposed DPP model along with the two strategies can achieve fairly competitive results against the state-of-the-art TTG systems.

With the explosive growth of microblogging service, Twitter has become a leading platform consisting of real-time world wide information. Users tend to explore breaking news or general topics in Twitter according to their interests. However, the explosive amount of incoming tweets leads users to information overload. Therefore, filtering interesting tweets based on users' interest profiles from real-time stream can be helpful for users to easily access the relevant and key information hidden among the tweets. On the other hand, real-time twitter stream contains enormous amount of noisy and redundant tweets. Hence, the filtering process should consider previously pushed interesting tweets to provide users with diverse tweets. What's more, different from traditional document summarization methods which focus on static dataset, the twitter stream is dynamic, fast-arriving and large-scale, which means we have to decide whether to filter the coming tweet for users from the real-time stream as early as possible. In this paper, we propose a novel adaptive evolutionary filtering framework to push interesting tweets for users from real-time twitter stream. First, we propose an adaptive evolutionary filtering algorithm to filter interesting tweets from the twitter stream with respect to user interest profiles. And then we utilize the maximal marginal relevance model in fixed time window to estimate the relevance and diversity of potential tweets. Besides, to overcome the enormous number of redundant tweets and characterize the diversity of potential tweets, we propose a hierarchical tweet representation learning model (HTM) to learn the tweet representations dynamically over time. Experiments on large scale real-time twitter stream datasets demonstrate the efficiency and effectiveness of our framework.

When searching over the microblogging, users prefer using queries including terms that represent some specific entities. Meanwhile, tweets, though limited within 140 characters, are often generated with one or more entities. Entities, as an important part of tweets, usually convey rich information for modeling relevance from new perspectives. In this paper, we propose a feedback entity model and integrate it into an adaptive language modeling framework in order to improve the retrieval performance. The feedback entity model is estimated with the latest entity-associated tweets based upon a regularized maximum likelihood criterion. More specifically, we assume that the entity-associated tweets are generated by a mixture model, which consists of the entity model, the domain-specific language model and the collection language model. Experimental results on two public Text Retrieval Conference (TREC) Twitter corpora demonstrate the significant superiority of our approach over the state-of-the-art baselines.