Zhumin Chen

Learning to recommend with social contextual information from implicit feedback

Recommender systems with social networks have been well studied in recent years. However, most of these methods ignore the social contextual information among users and items, which is significant and useful for predicting users’ preferences in many recommendation problems. Moreover, most existing social recommendation methods have been proposed for the scenarios where users can provide explicit ratings. But in fact, the explicit feedback is not always available, most of the feedback in real social networks is not explicit but implicit. Motivated by above observations, we propose a unified ranking framework fusing social contextual information and common social relations for implicit feedback. Specifically, we first extend the user latent features by the implicit interest deduced from social context, and then we integrate the common social relations as factorization terms to further improve recommendation quality. Finally, we optimize our model in a Bayesian personalized ranking framework. The experiments on real-world dataset show that our approach outperforms the other state-of-the-art algorithms in terms of AUC, NDCG and Pre@3. This result demonstrates the importance of social context and common social relations for the formation of the implicit ratings.

Neural Attentive Session-based Recommendation

Given e-commerce scenarios that user profiles are invisible, session-based recommendation is proposed to generate recommendation results from short sessions. Previous work only considers the users sequential behavior in the current session, whereas the users main purpose in the current session is not emphasized. In this paper, we propose a novel neural networks framework, i.e., Neural Attentive Recommendation Machine (NARM), to tackle this problem. Specifically, we explore a hybrid encoder with an attention mechanism to model the users sequential behavior and capture the users main purpose in the current session, which are combined as a unified session representation later. We then compute the recommendation scores for each candidate item with a bi-linear matching scheme based on this unified session representation. We train NARM by jointly learning the item and session representations as well as their matchings. We carried out extensive experiments on two benchmark datasets. Our experimental results show that NARM outperforms state-of-the-art baselines on both datasets. Furthermore, we also find that NARM achieves a significant improvement on long sessions, which demonstrates its advantages in modeling the users sequential behavior and main purpose simultaneously.

Web page publication time detection and its application for page rank

Publication Time (P-time for short) of Web pages is often required in many application areas. In this paper, we address the issue of P-time detection and its application for page rank. We first propose an approach to extract P-time for a page with explicit P-time displayed on its body. We then present a method to infer P-time for a page without P-time. We further introduce a temporal sensitive page rank model using P-time. Experiments demonstrate that our methods outperform the baseline methods significantly.

Leveraging Contextual Sentence Relations for Extractive Summarization Using a Neural Attention Model

As a framework for extractive summarization, sentence regression has achieved state-of-the-art performance in several widely-used practical systems. The most challenging task within the sentence regression framework is to identify discriminative features to encode a sentence into a feature vector. So far, sentence regression approaches have neglected to use features that capture contextual relations among sentences. We propose a neural network model, Contextual Relation-based Summarization (CRSum), to take advantage of contextual relations among sentences so as to improve the performance of sentence regression. Specifically, we first use sentence relations with a word-level attentive pooling convolutional neural network to construct sentence representations. Then, we use contextual relations with a sentence-level attentive pooling recurrent neural network to construct context representations. Finally, CRSum automatically learns useful contextual features by jointly learning representations of sentences and similarity scores between a sentence and sentences in its context. Using a two-level attention mechanism, CRSum is able to pay attention to important content, i.e., words and sentences, in the surrounding context of a given sentence. We carry out extensive experiments on six benchmark datasets. CRSum alone can achieve comparable performance with state-of-the-art approaches; when combined with a few basic surface features, it significantly outperforms the state-of-the-art in terms of multiple ROUGE metrics.

Improving Image Annotation via Ranking-Oriented Neighbor Search and Learning-Based Keyword Propagation

Automatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associated with the neighbors to the new image. In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest‐neighbor–based scheme. In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking‐oriented neighbor search mechanism (RNSM), where the ordering of labeled images is optimized directly without going through the intermediate step of distance prediction. In the phase of keyword propagation, different from existing work using simple heuristic rules to select the propagated keywords, we present a learning‐based keyword propagation strategy (LKPS), where a scoring function is learned to evaluate the relevance of keywords based on their multiple relations with the nearest neighbors. Extensive experiments on the Corel 5K data set and the MIR Flickr data set demonstrate the effectiveness of our approach.

Effective and effortless features for popularity prediction in microblogging network

Predicting popularity of online contents is of remarkable practical value in various business and administrative applications. Existing studies mainly focus on finding the most effective features for prediction. However, some effective features, such as structural features which are extracted from the underlying user network, are hard to access. In this paper, we aim to identify features that are both effective and effortless (easy to obtain or compute). Experiments on Sina Weibo show the effectiveness and effortlessness of the temporal features and satisfying prediction performance can be obtained based on only the temporal features of first 10 retweets.

Social Trust Aware Item Recommendation for Implicit Feedback

Social trust aware recommender systems have been well studied in recent years. However, most of existing methods focus on the recommendation scenarios where users can provide explicit feedback to items. But in most cases, the feedback is not explicit but implicit. Moreover, most of trust aware methods assume the trust relationships among users are single and homogeneous, whereas trust as a social concept is intrinsically multi-faceted and heterogeneous. Simply exploiting the raw values of trust relations cannot get satisfactory results. Based on the above observations, we propose to learn a trust aware personalized ranking method with multi-faceted trust relations for implicit feedback. Specifically, we first introduce the social trust assumption — a user’s taste is close to the neighbors he/she trusts — into the Bayesian Personalized Ranking model. To explore the impact of users’ multi-faceted trust relations, we further propose a categorysensitive random walk method CRWR to infer the true trust value on each trust link. Finally, we arrive at our trust strength aware item recommendation method SocialBPRCRWR by replacing the raw binary trust matrix with the derived real-valued trust strength. Data analysis and experimental results on two real-world datasets demonstrate the existence of social trust influence and the effectiveness of our social based ranking method SocialBPRCRWR in terms of AUC (area under the receiver operating characteristic curve).

Understanding Temporal Intent of User Query Based on Time-Based Query Classification

Web queries are time sensitive which implies that user’s intent for information changes over time. How to recognize temporal intents behind user queries is crucial towards improving the performance of search engines. However, to the best of our knowledge, this problem has not been studied in existing work. In this paper, we propose a time-based query classification approach to understand user’s temporal intent automatically. We first analyzed the shared features of queries’ temporal intent distributions. Then, we present a query taxonomy which group queries according to their temporal intents. Finally, for a new given query, we propose a machine learning method to decide its class in terms of its search frequency over time recorded in Web query logs. Experiments demonstrate that our approach can understand users’ temporal intents effectively.

Learning to Rank Images for Complex Queries in Concept-based Search

Concept-based image search is an emerging search paradigm that utilizes a set of concepts as intermediate semantic descriptors of images to bridge the semantic gap. Typically, a user query is rather complex and cannot be well described using a single concept. However, it is less effective to tackle such complex queries by simply aggregating the individual search results for the constituent concepts. In this paper, we propose to introduce the learning to rank techniques to concept-based image search for complex queries. With freely available social tagged images, we first build concept detectors by jointly leveraging the heterogeneous visual features. Then, to formulate the image relevance, we explicitly model the individual weight of each constituent concept in a complex query. The dependence among constituent concepts, as well as the relatedness between query and non-query concepts, are also considered through modeling the pairwise concept correlations in a factorization way. Finally, we train our model to directly optimize the image ranking performance for complex queries under a pairwise learning to rank framework. Extensive experiments on two benchmark datasets well verified the promise of our approach.

Mining and ranking users' intents behind queries

Abstract How to understand intents behind user queries is crucial towards improving the performance of Web search systems. NTCIR-11 IMine task focuses on this problem. In this paper, we address the NTCIR-11 IMine task with two phases referred to as Query Intent Mining (QIM) and Query Intent Ranking (QIR). (I) QIM is intended to mine users’ potential intents by clustering short text fragments related to the given query. (II) QIR focuses on ranking those mined intents in a proper way. Two challenges exist in handling these tasks. (II) How to precisely estimate the intent similarity between user queries which only consist of a few words. (2) How to properly rank intents in terms of multiple factors, e.g. relevance, diversity, intent drift and so on. For the first challenge, we first investigate two interesting phenomena by analyzing query logs and document datasets, namely “Same-Intent-Co-Click” (SICC) and “Same-Intent-Similar-Rank” (SISR). SICC means that when users issue different queries, these queries represent the same intent if they click on the same URL. SISR means that if two queries denote the same intent, we should get similar search results when issuing them to a search engine. Then, we propose similarity functions for QIM based on the two phenomena. For the second challenge, we propose a novel intent ranking model which considers multiple factors as a whole. We perform extensive experiments and an interesting case study on the Chinese dataset of NTCIR-11 IMine task. Experimental results demonstrate the effectiveness of our proposed approaches in terms of both QIM and QIR.