Search

Sentiment analysis, which is a fundamental research in the field of natural language processing and artificial intelligence field, has received much attention these years because of its practical applicability and the challenges. However, existing methods only focus on local text information and ignore the background knowledge (such as the director of a movie, the producer of a product). In this paper, we propose a novel LSTM with Background Knowledge Attention Model (LSTM-BKAM) for sentiment analysis. Our model incorporates background knowledge based attentions over different semantic parts of a sentence. The experiment results show that our model achieves state-of-the-art, and substantially better than other approaches.

How people divide their attention across their friends can help to understand key issues in the realm of geopolitics. Such attention exploration allows us to compare people who focus a large portion of their attention on a small set of close friends with those disperse their attention more widely. Using 2.5 million twitter data written by 130 thousands users, we find the balance of attention is a relatively stable property of people across different modalities of interaction. It displays subtle variation across people with different characteristics and different modalities of interaction. Specifically, people’s attention is more focused in mention interactions, while those active in socialization tend to allocate higher portion of total attention to their close friends. Besides external interactions, people’s inner interests also affect their attention allocation. People spreading multiple memes tend to be focused, and those with more even distribution of memes are focused on their intimate friends. Finally, people’s relationships also plays an important role in their attention allocation. People are more likely to focus their attention on those most like them, and this similarity sequentially enhances the intimate relationship between them.

Cyber crimes including computer virus/malwares, spam, illegal sales, and phishing websites are proliferated aggressively via the disguised Uniform Resource Locators (URL). Although numerous studies were conducted for the URL classification task, the traditional URL classification solutions retreated due to the hand-crafted feature engineering and the boom of newly generated URLs. In this paper, we study the representation learning of URLs, and explore the URL classification using deep learning. Specifically, we propose URL2vec to extract both the structural and lexical features of URLs, and apply temporal convolutional network (TCN) for the URL classification task. The experimental results show that URL2vec outperforms both word2vec and character-level embedding for URL representation, and TCN achieves the best performance than baselines with the precision up to 95.97%.

Topic classification plays an important role in facilitating security-related applications, which can help people reduce data scope and acquire key information quickly. Conversation is one of the important ways of communication between people. The utterances in a conversation may contain vital clues, such as people’s opinions, emotions and political slants. To explore more effective approaches for Chinese conversational topic classification, in this paper, we propose a neural network architecture with pre-trained contextualized representation. We firstly apply pretrained BERT model to fine-tune and generate the conversational embeddings, which are the inputs of our neural network models. Then we design several models based on neural networks to extract task-oriented advanced features for topic classification. Experimental results indicate that the models based on our neural network architecture all outperform the baseline only fine-tuned with the pre-trained BERT model. It demonstrates that the pretrained representations are effective to Chinese conversational topic classification, and the proposed architecture can further capture the salient features from the representations. And we release the code and dataset of this paper that can be obtained from https://github.com/njoe9/pretrained_representation.

Healthcare-seeking behavior (HSB) is the motivation of formulating, developing and changing healthcare policy and medical insurance system, also the important reference of reforming and improving healthcare systems. This paper mainly focused on exploring ‘Patterns-Drivers’ of HSB using a case study on Beijing Hand-Foot-Mouth Disease (HFMD) in China. We extracted the index for HSB and constructed the networks using the heterogeneous information from patients’ records, clarified the spatial-temporal distribution of HSB and examined spatial association between HSB and socioeconomic factors using Geographically Weighted Regression. It was found that HFMD morbidity, the spatial distribution of kindergarten, the scale of the public infrastructures such as the park and the toilet was the important local drivers of HSB. The outcome based on the application of complex networks, geographic information system and spatial statistical techniques would provide valuable information supporting the optimal allocation of health resources and decision-making in disease control and prevention.

Detecting potential marketing pattern risks and preventing them can help enterprises lift operation efficiencies and reduce outlay costs. In this paper, we elaborate an ingenious method based on semi-supervised learning to identify latent marketing pattern risks for enterprises.

Image aesthetic quality assessment has demonstrated tremendous success in variety of application domains in recent years. This field has been growing so rapidly that various approaches have been proposed trying to solve this challenging problem. This report presents a comprehensive survey on image aesthetic quality assessment, mainly focus on the contributions and novelties of the existing approaches recently. In this work, we firstly illustrate datasets related to image aesthetics and investigate feature extractions. Then five different aesthetic tasks are reviewed, including aesthetic classification, aesthetic regression, aesthetic distribution, aesthetic factors and aesthetic description. In addition, we reviewed recent applications concerning image aesthetics. Finally, different evaluation criterions in different literatures are summarized. We hope the survey could serve as a comprehensive reference and be useful for those who are interested in exploiting image aesthetic for their research.

Online emotion diffusion is a compound process that involves interactions with multiple modalities. For instance, different behaviors influence the velocity and scale of emotion diffusion in online communities. Depicting and predicting massive online emotions helps to guide the trend of emotion evolution, thus avoiding unprecedented damages in crises. However, most existing work tries to depict and predict online emotions based on models not considering related modalities. There still lacks an efficient modeling framework that promotes performance by leveraging multi-modality knowledge, and quantifies the interactions among different modalities. In this paper, we elaborate a computational model to jointly depict online emotions and behaviors. By introducing a common structure, we can quantify how user emotions interact with the corresponding behaviors. To scale up to large dataset, we propose a hierarchical optimization algorithm to accelerate the convergence of the model. Evaluation on Sina Weibo dataset suggests that prediction error rate is lowered by 69 percent with the proposed model. In addition, the proposed model helps to explain how user emotions influence consequent behaviors in extreme situations.

The proliferation of social media has increased the competition among different memes, which can be free texts, trending catchphrases, or micro media. As human attention is limited, these memes compete with each other, and go in and out of popularity at a rapid pace, sometimes even faster than we can recognize. Popular memes often shape the mindsets of online communities, and also shed light on their future tendencies. Considering the huge volume of memes generated and their continuous mutations, extracting and tracing online memes automatically is rather challenging. In this paper, we propose an automatic meme extraction algorithm. The proposed algorithm extracts massive memes based on phrases independency, and clusters phrase variants of a single meme efficiently. Evaluation on measles outbreak in the USA in 2015 indicates that the proposed algorithm could extract typical memes reflecting the fierce campaign between the pro-vaccination community and the anti-vaccination community. In both communities, memes are power-law distributed, and popular ones have many variants that appear more frequently. By tracing the evolution of online memes, we uncover that popular memes converge and generate peaks at times. Though the pro-vaccination community and the anti-vaccination community may focus on similar memes, they comprehend memes from totally different perspectives and deliver opposing opinions of measles vaccination.

Illicit trade in tobacco products (ITTP) would severely disrupt the market order, greatly threaten citizen's health, and damage the interests of the nation and the consumers, which has attracted great attention of tobacco monopoly administration. Quick and correct detection of the changes and the drivers of ITTP activity would be very significant to the surveillance, tracing, early warning, prediction, prevention and control of the illicit tobacco trade, which are very important challenges for tobacco monopoly administrations in China. In this paper, we introduce spatial-temporal analysis techniques into detecting the spatial-temporal patterns and drivers of ITTP based on the dataset provided by tobacco monopoly administration of Changsha county in Hunan province, China. The results suggested that ITTP in the county mostly occurred along the downtown-county borders, or nearby the toll stations located on the highway, logistics and freight distribution center and the junction of neighboring areas. Positive correlations were found between illegal rate and population density, the number of kindergartens and nursery schools, proximity to the borders, the number of the pupils and the middle school students, which was consistent with the previous study and social etiquette. This study could provide important intelligence and clues for the decision makers and make sure that the resources should be allocated as effectively as possible.

Emotion entrainment, which is generally defined as the synchronous convergence of human emotions, performs many important social functions. However, what the specific mechanisms of emotion entrainment are beyond in-person interactions, and how human emotions evolve under different entrainment patterns in large-scale social communities, are still unknown. In this paper, we aim to examine the massive emotion entrainment patterns and understand the underlying mechanisms in the context of social media. As modeling emotion dynamics on a large scale is often challenging, we elaborate a pragmatic framework to characterize and quantify the entrainment phenomenon. By applying this framework on the datasets from two large-scale social media platforms, we find that the emotions of online users entrain through social networks. We further uncover that online users often form their relations via dual entrainment, while maintain it through single entrainment. Remarkably, the emotions of online users are more convergent in nonreciprocal entrainment. Building on these findings, we develop an entrainment augmented model for emotion prediction. Experimental results suggest that entrainment patterns inform emotion proximity in dyads, and encoding their associations promotes emotion prediction. This work can further help us to understand the underlying dynamic process of large-scale online interactions and make more reasonable decisions regarding emergency situations, epidemic diseases, and political campaigns in cyberspace.

Emotion plays an important role in shaping public policy and business decisions. The growth of social media has allowed people to express their emotion publicly in an unprecedented manner. Textual content and user linkages fostered by social media networks can be used to examine emotion types, intensity, and contagion. However, research into how emotion evolves and entrains in social media that influence security issues is scarce. In this research, we developed an approach to analyzing emotion expressed in political social media. We compared two methods of emotion analysis to identify influential users and to trace their contagion effects on public emotion, and report preliminary findings of analyzing the emotion of 105,304 users who posted 189,012 tweets on the U.S. immigration and border security issues in November 2014. The results provide strong implication for understanding social actions and for collecting social intelligence for security informatics. This research should contribute to helping decision makers and security personnel to use public emotion effectively to develop appropriate strategies.

The rapid proliferation of online social networks has greatly boosted the dissemination and evolution of online memes, which can be free text, trending catchphrase, or micro media. However, this information abundance is exceeding the capability of the public to consume it, especially in unusual situations such as emergency management, intelligence acquisition, and crime analysis. Thus, there calls for a reliable approach to rank meme appropriately according to its influence, which will let the public focus on the most important memes without sinking into the information flood. However, studying meme in any detail on a large scale proves to be challenging. Previous bottom-up approaches are often highly complex, while the more recent top-down network analysis approaches lack detailed modeling for meme dynamics. In this paper, we first present a formal definition for meme ranking task, and then introduce a scheme for meme ranking in the context of online social networks (OSN). To the best of our knowledge, this is the first time that memes have been ranked in a model-free manner. Empirical results on two emergency events indicate that our scheme outperforms several benchmark approaches. This scheme is also robust by insensitive to sample rate. In light of the scheme's fine-grain modeling on meme dynamics, we also reveal two key factors affecting meme influence.

Sentiment analysis has now become a popular research problem to tackle in NLP field. However, there are very few researches conducted on sentiment analysis for Chinese. Progress is held back due to lack of large and labelled corpus and powerful models. To remedy this deficiency, we build a Chinese Sentiment Treebank over social data. It concludes 13550 labeled sentences which are from movie reviews. Furthermore, we introduce a novel Recursive Neural Deep Model (RNDM) to predict sentiment label based on recursive deep learning. We consider the problem of classifying one sentence by overall sentiment, determining a review is positive or negative. On predicting sentiment label at sentence level, our model outperforms other commonly used baselines, such as Naive Bayes, Maximum Entropy and SVM, by a large margin.

Discovering temporal patterns and changes in tobacco use has important practical implications in tobacco control. This paper presents one of the first comprehensive international studies of seasonal smoking patterns based on online searches performed. Using periodogram and cross-correlation, we find that smoking-related search behavior shows strong seasonality effect across countries. In addition, there are significant pairwise associations between such seasonality in different countries.

This paper presents a novel application of incorporating Alternating Structure Optimization (ASO) to conduct the task of text chunking of Semantic Role Labeling (SRL) in Chinese texts. ASO is a competent linear algorithm based on the theory of Multi-task Learning. In this paper, by constructing several SRL tasks to constitute a multi-task, we are able to encode the inference obtained by ASO algorithm as additional feature to further boost the performance of the target task employing Conditional Random Fields (CRFs). To our knowledge, our method is the first that incorporates multi-task learning into a statistical model in SRL for Chinese texts. We evaluate our approach on Penn Treebank data sets and obtain encouraging result.

Cross-document coreference resolution, which is an important subtask in natural language processing systems, focus on the problem of determining if two mentions from different documents refer to the same entity in the world. In this paper we present a two-step approach, employing a classification and clusterization phase. In a novel way, the clusterization is produced as a graph cutting algorithm, namely, neural networks-based BestCut (NBCut). To our knowledge, our system is the first that employs a statistical model in graph partitioning. We evaluate our approach on ACE 2008 cross-document coreference resolution data sets and obtain encouraging result, indicating that on named noun phrase coreference task, the approach holds promise and achieves competitive performance.