Mengting Hu, Shiwan Zhao, Li Zhang, Keke Cai, Zhong Su, Renhong Cheng, Xiaowei Shen. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

State-of-the-art methods for product recommendation encounter a significant performance drop in categories where a user has no purchase history. This problem needs to be addressed since current online retailers are moving beyond single category and attempting to be diversified. In this article, we investigate the challenging problem of product recommendation in unexplored categories and discover that the price, a factor comparable across categories, can improve the recommendation performance significantly. We introduce the price utility concept to characterize users’ sense of price and propose three different utility functions. We show that user price preference in a category is a distribution and we mine typical user price preference patterns based on three different types of distance between distributions. We fuse user price preference through regularization and joint factorization to boost recommendation performance in both browsing and buying shopping orientations. Experimental results show that fusing user price preference improves performance in a series of recommendation tasks: unexplored category recommendation, product recommendation under a given unexplored category, and product recommendation under generic unexplored categories.

Finding a subset of users to statistically represent the original social network is a fundamental issue in Social Network Analysis (SNA). The problem has not been extensively studied in existing literature. In this paper, we present a formal definition of the problem of \textbf{sampling representative users} from social network. We propose two sampling models and theoretically prove their NP-hardness. To efficiently solve the two models, we present an efficient algorithm with provable approximation guarantees. Experimental results on two datasets show that the proposed models for sampling representative users significantly outperform (+6\%-23\% in terms of Precision@100) several alternative methods using authority or structure information only. The proposed algorithms are also effective in terms of time complexity. Only a few seconds are needed to sampling ~300 representative users from a network of 100,000 users.All data and codes are publicly available.

State-of-the-art methods for product recommendation encounter significant performance drop in categories where a user has no purchase history. This problem needs to be addressed since current online retailers are moving beyond single category and attempting to be diversified. In this paper, we investigate the challenge problem of product recommendation in unexplored categories and discover that the price, a factor transferrable across categories, can improve the recommendation performance significantly. Through our investigation, we address four research questions progressively: 1) what is the impact of unexplored category on recommendation performance? 2) How to represent the price factor from the recommendation point of view? 3) What does price factor across categories mean to recommendation? 4) How to utilize price factor across categories for recommendation in unexplored categories? Based on a series of experiments and analysis conducted on a dataset collected from a leading E-commerce website, we discover valuable findings for the above four questions: first, unexplored categories cause performance drop by 40% relatively for current recommendation systems; second, the price factor can be represented as either a quantity for a product or a distribution for a user to improve performance; third, consumer behavior with respect to price factor across categories is complicated and needs to be carefully modeled; finally and most importantly, we propose a new method which encodes the two perspectives of the price factor. The proposed method significantly improves the recommendation performance in unexplored categories over the state-of-the-art baseline systems and shortens the performance gap by 43% relatively.

This paper is concerned with the problem of mining social emotions from text. Recently, with the fast development of web 2.0, more and more documents are assigned by social users with emotion labels such as happiness, sadness, and surprise. Such emotions can provide a new aspect for document categorization, and therefore help online users to select related documents based on their emotional preferences. Useful as it is, the ratio with manual emotion labels is still very tiny comparing to the huge amount of web/enterprise documents. In this paper, we aim to discover the connections between social emotions and affective terms and based on which predict the social emotion from text content automatically. More specifically, we propose a joint emotion-topic model by augmenting Latent Dirichlet Allocation with an additional layer for emotion modeling. It first generates a set of latent topics from emotions, followed by generating affective terms from each topic. Experimental results on an online news collection show that the proposed model can effectively identify meaningful latent topics for each emotion. Evaluation on emotion prediction further verifies the effectiveness of the proposed model.

Patents are of crucial importance for businesses, because they provide legal protection for the invented techniques, processes or products. A patent can be held for up to 20 years. However, large maintenance fees need to be paid to keep it enforceable. If the patent is deemed not valuable, the owner may decide to abandon it by stopping paying the maintenance fees to reduce the cost. For large companies or organizations, making such decisions is difficult because too many patents need to be investigated. In this paper, we introduce the new patent mining problem of automatic patent maintenance prediction, and propose a systematic solution to analyze patents for recommending patent maintenance decision. We model the patents as a heterogeneous time-evolving information network and propose new patent features to build model for a ranked prediction on whether to maintain or abandon a patent. In addition, a network-based refinement approach is proposed to further improve the performance. We have conducted experiments on the large scale United States Patent and Trademark Office (USPTO) database which contains over four million granted patents. The results show that our technique can achieve high performance.

We study a novel problem of social context summarization for Web documents. Traditional summarization research has focused on extracting informative sentences from standard documents. With the rapid growth of online social networks, abundant user generated content (e.g., comments) associated with the standard documents is available. Which parts in a document are social users really caring about? How can we generate summaries for standard documents by considering both the informativeness of sentences and interests of social users? This paper explores such an approach by modeling Web documents and social contexts into a unified framework. We propose a dual wing factor graph (DWFG) model, which utilizes the mutual reinforcement between Web documents and their associated social contexts to generate summaries. An efficient algorithm is designed to learn the proposed factor graph model.Experimental results on a Twitter data set validate the effectiveness of the proposed model. By leveraging the social context information, our approach obtains significant improvement (averagely +5.0%-17.3%) over several alternative methods (CRF, SVM, LR, PR, and DocLead) on the performance of summarization.

Social influence is a complex and subtle force that governs the dynamics of social networks. In the past years, a lot of research work has been conducted to understand the spread patterns of social influence. However, most of approaches assume that influence exists between users with active social interactions, but ignore the question of what kind of influence happens between them. As such one interesting and also fundamental question is raised here: "in a social network, could the social connection reflect users'influence from both positive and negative aspects?". To this end, an Opinion Oriented Link Analysis Model (OOLAM) is proposed in this paper to characterize users' influence personae in order to exhibit their distinguishing influence ability in the social network. In particular, three types of influence personae are generalized and the problem of influence persona discovery is formally defined. Within the OOLAM model, two factors, i.e., opinion consistency and opinion creditability, are defined to capture the persona information from public opinion perspective. Extensive experimental studies have been performed to demonstrate the effectiveness of the proposed approach on influence persona analysis using real web data sets.

Retweeting is an important action (behavior) on Twitter, indicating the behavior that users re-post microblogs of their friends. While much work has been conducted for mining textual content that users generate or analyzing the social network structure, few publications systematically study the underlying mechanism of the retweeting behaviors. In this paper, we perform an interesting analysis for the problem on Twitter. We have found that almost 25.5% of the tweets posted by users are actually retweeted from friends' blog spaces. Our investigation unveils that for the retweet behaviors, some statistics still follows the power law distribution, while some others violate the state-of-the-art distribution for Web. Based on these important observations, we propose a factor graph model to predict users' retweeting behaviors. Experimental results on the Twitter data set show that our method can achieve a precision of 28.81% and recall of 37.33% for prediction of the retweet behaviors.

The emergence of new social media such as blogs, message boards, news, and web content in general has dramatically changed the ecosystems of corporations. Consumers, non-profit organizations, and other forms of communities are extremely vocal about t

This paper is concerned with the problem of social affective text mining, which aims to discover the connections between social emotions and affective terms based on user-generated emotion labels. We propose a joint emotion-topic model by augmenting latent Dirichlet allocation with an additional layer for emotion modeling. It first generates a set of latent topics from emotions, followed by generating affective terms from each topic. Experimental results on an online news collection show that the proposed model can effectively identify meaningful latent topics for each emotion. Evaluation on emotion prediction further verifies the effectiveness of the proposed model.

It is well known that Web users create links with different intentions. However, a key question, which is not well studied, is how to categorize the links and how to quantify the strength of the influence of a Web page on another if there is a link between the two linked Web pages. In this paper, we focus on the problem of link semantics analysis, and propose a novel supervised learning approach to build a model, based on a training link-labeled and link-weighted graph where a link-label represents the category of a link and a link-weight represents the influence of one web page on the other in a link. Based on the model built, we categorize links and quantify the influence of Web pages on the others in a large graph in the same application domain. We discuss our proposed approach, namely pairwise restricted Boltzmann machines (PRBMs), and conduct extensive experimental studies to demonstrate the effectiveness of our approach using large real datasets.

This paper addresses several key issues in the ArnetMiner system, which aims at extracting and mining academic social networks. Specifically, the system focuses on: 1) Extracting researcher profiles automatically from the Web; 2) Integrating the publication data into the network from existing digital libraries; 3) Modeling the entire academic network; and 4) Providing search services for the academic network. So far, 448,470 researcher profiles have been extracted using a unified tagging approach. We integrate publications from online Web databases and propose a probabilistic framework to deal with the name ambiguity problem. Furthermore, we propose a unified modeling approach to simultaneously model topical aspects of papers, authors, and publication venues. Search services such as expertise search and people association search have been provided based on the modeling results. In this paper, we describe the architecture and main features of the system. We also present the empirical evaluation of the proposed methods.

The emergence of new social media such as blogs, message boards, news, and Web content in general has dramatically changed the ecosystems of corporations. Consumers, non-profit organizations, and other forms of communities are extremely vocal about their opinions and perceptions on companies and their brands on the Web. The ability to leverage such "voice of the Web" to gain consumer, brand, and market insights can be truly differentiating and valuable to todaypsilas corporations. In particular, one important form of insights can be derived from sentiment analysis on Web content. Sentiment analysis traditionally emphasizes on classification of Web comments into positive, neutral, and negative categories. This paper goes beyond sentiment classification by focusing on techniques that could detect the topics that are highly correlated with the positive and negative opinions. Such techniques, when coupled with sentiment classification, can help the business analysts to understand both the overall sentiment scope as well as the drivers behind the sentiment. In this paper, we describe our overall sentiment analysis system that consists of such sentiment analysis techniques. We then detail a novel topic detection method using point-wise mutual information and term frequency distribution. We demonstrate the effectiveness of our overall approaches via several case studies on different social media data sets.

Modern corporations operate in an extremely complex environment and strongly depend on all kinds of information resources across the enterprise. Unfortunately, with the growth of an enterprise, its information resources are not only heterogeneous but also distributed in physically different systems and databases. How to effectively exploit information across the enterprise is becoming a critical but hard problem. In recent years, metadata which is the detailed description of the data is used to efficiently exploit information resources in the web. The World Wide Web Consortium (W3C) recommends the resource description framework (RDF) as a standard for the definition and use of metadata descriptions of resources in the web. In this paper, we present an RDF storage and query system called RStar for enterprise resource management. RStar uses a relational database as the persistent data store and defines RStar Query Language (RSQL) for resource retrieval. Currently, most of existing RDF storage and query systems are evaluated on small data sets and no detailed performance analysis is given for such systems. Therefore, we conduct extensive experiments on a large scale data set to investigate the performance problem in RDF storage. Such analysis will be helpful for designing RDF storage and query systems as well as for understanding not well-solved issues in RDF based enterprise resource management. In addition, experiences and lessons learned in our implementation are presented for further research and development.

In this paper we study the problem of collecting training samples for building enterprise taxonomies. We develop a computer-aided tool named InfoAnalyzer, which can effectively assist the enterprise to prepare large set of samples used for machine learning in text categorization. In our system, the enterprise category tree is initially defined by some keywords, then the Google search engine is used to construct a small set of labeled documents, and topic tracking algorithm based on document length normalization is applied to enlarge the training corpus on the bases of the seed stories. Furthermore, we design a method to check the consistency of the training corpus. Experiments show that the training corpus is good enough for statistical classification methods and meets human's requirements as well.

In this paper we study the problem of finding most topical named entities among all entities in a document, which we refer to as focused named entity recognition. We show that these focused named entities are useful for many natural language processing applications, such as document summarization, search result ranking, and entity detection and tracking. We propose a statistical model for focused named entity recognition by converting it into a classification problem. We then study the impact of various linguistic features and compare a number of classification algorithms. From experiments on an annotated Chinese news corpus, we demonstrate that the proposed method can achieve near human-level accuracy.