A Novel Approach Based on Multi-View Content Analysis and Semi-Supervised Enrichment for Movie Recommendation

Although many existing movie recommender systems have investigated recommendation based on information such as clicks and tags, much less efforts have been made to explore the multimedia content of movies, which has potential information for the elicitation of the user’s visual and musical preferences.In this paper, we explore the content from three media types (image, text, audio) and propose a novel multi-view semi-supervised movie recommendation method, which represents each media type as a view space for movies.The three views of movies are integrated to predict the rating values under the multi-view framework.Furthermore, our method considers the casual users who rate limited movies.The algorithm enriches the user profile with a semi-supervised way when there are only few rating histories.Experiments indicate that the multimedia content analysis reveals the user’s profile in a more comprehensive way.Different media types can be a complement to each other for movie recommendation.And the experimental results validate that our semi-supervised method can effectively enrich the user profile for recommendation with limited rating history.     

基于Movielens电影数据的可视分析

目前,随着电影数据逐渐被人们获取,关于电影数据的研究可以给人们带来很多启发。分析电影流派的演变规律,可以为导演提供电影题材建议;分析经济和电影之间的关系,可以找到电影演变的原因;研究高评分电影在时间上的规律,可以指导导演选择电影的上映时间。但是,由于电影包含电影名称、所属流派、评分等多重属性,一般的研究方法不足以发现并直观地呈现电影数据隐含的规律。用可视化与可视分析的方法分析电影数据,设计了一系列相互关联的可视化视图,从多个时间尺度角度分析电影流派的时间演变,通过增长率曲线图研究电影数量和经济的相关关系,并设计饼图集来发现高评分电影在时间、流派上的规律。     

A collaborative user-centered framework for recommending items in Online Social Networks

Recommender Systems are more and more playing an important role in our life, representing useful tools helping users to find “what they need” from a very large number of candidates and supporting people in making decisions in various contexts: what items to buy, which movie to watch, or even who they can invite to their social network, etc. In this paper, we propose a novel collaborative user-centered recommendation approach in which several aspects related to users and available in Online Social Networks – i.e. preferences (usually in the shape of items’ metadata), opinions (textual comments to which it is possible to associate a sentiment), behavior (in the majority of cases logs of past items’ observations made by users), feedbacks (usually expressed in the form of ratings) – are considered and integrated together with items’ features and context information within a general framework that can support different applications using proper customizations (e.g., recommendation of news, photos, movies, travels, etc.). Experiments on system accuracy and user satisfaction in several domains shows how our approach provides very promising and interesting results.     

基于用户行为模型和蚁群聚类的协同过滤推荐算法

协同过滤技术是推荐系统中应用最为广泛的技术之一,用户的相似性度量是整个算法的核心要素,会对推荐算法准确率产生很大的影响.传统的协同过滤算法过度依赖用户评分机制,影片自身的标签信息没有被考虑为一个影响因素,在用户聚类时采用K近邻算法,会由于评分矩阵过于稀疏而难以收敛.同时,传统推荐技术仅基于用户历史行为进行推荐,无法为新用户提供合理的推荐.针对以上问题,提出了一种基于用户行为建模的蚁群聚类和协同过滤算法相结合的影片推荐技术.     

QuickLook: Movie summarization using scene-based leading characters with psychological cues fusion

Due to recent advances in the film industry, the production of movies has grown exponentially, which has led to challenges in what is referred to as discoverability: given the overwhelming number of choices, choosing which film to watch has become a tedious task for audiences. Movie summarization (MS) could help, as it presents the central theme of the movie in a compact format and makes browsing more efficient for the audience. In this paper, we present an automatic MS framework coined as ‘QuickLook’, which identifies the leading characters and fuses multiple cues extracted from a movie. Firstly, the movie data is preprocessed for its division into scenes, followed by shot segmentation. Secondly, the leading characters in each segmented scene are determined. Next, four visual cues that capture the film's scenic beauty, memorability, informativeness and emotional resonance are extracted from shots containing the leading characters. These extracted features are then intelligently fused based on the assignment of different weights; shots with a fusion score above a certain threshold are selected for the final summary. The proposed MS framework is assessed by comparison with official trailers from ten Hollywood movies, providing a novel baseline for future fair comparison in the MS literature. The proposed framework is shown to outperform other state-of-the-art MS methods in terms of enjoyability and informativeness.     

Argument-based mixed recommenders and their application to movie suggestion

Recommender systems have become prevalent in recent years as they help users to access relevant items from the vast universe of possibilities available these days. Most existing research in this area is based purely on quantitative aspects such as indices of popularity or measures of similarity between items or users. This work introduces a novel perspective on movie recommendation that combines a basic quantitative method with a qualitative approach, resulting in a family of mixed character recommender systems. The proposed framework incorporates the use of arguments in favor or against recommendations to determine if a suggestion should be presented or not to a user. In order to accomplish this, Defeasible Logic Programming (DeLP) is adopted as the underlying formalism to model facts and rules about the recommendation domain and to compute the argumentation process. This approach has a number features that could be proven useful in recommendation settings. In particular, recommendations can account for several different aspects (e.g., the cast, the genre or the rating of a movie), considering them all together through a dialectical analysis. Moreover, the approach can stem for both content-based or collaborative filtering techniques, or mix them in any arbitrary way. Most importantly, explanations supporting each recommendation can be provided in a way that can be easily understood by the user, by means of the computed arguments. In this work the proposed approach is evaluated obtaining very positive results. This suggests a great opportunity to exploit the benefits of transparent explanations and justifications in recommendations, sometimes unrealized by quantitative methods.     

A content-collaborative recommender that exploits WordNet-based user profiles for neighborhood formation

Collaborative and content-based filtering are the recommendation techniques most widely adopted to date. Traditional collaborative approaches compute a similarity value between the current user and each other user by taking into account their rating style, that is the set of ratings given on the same items. Based on the ratings of the most similar users, commonly referred to as neighbors, collaborative algorithms compute recommendations for the current user. The problem with this approach is that the similarity value is only computable if users have common rated items. The main contribution of this work is a possible solution to overcome this limitation. We propose a new content-collaborative hybrid recommender which computes similarities between users relying on their content-based profiles, in which user preferences are stored, instead of comparing their rating styles. In more detail, user profiles are clustered to discover current user neighbors. Content-based user profiles play a key role in the proposed hybrid recommender. Traditional keyword-based approaches to user profiling are unable to capture the semantics of user interests. A distinctive feature of our work is the integration of linguistic knowledge in the process of learning semantic user profiles representing user interests in a more effective way, compared to classical keyword-based profiles, due to a sense-based indexing. Semantic profiles are obtained by integrating machine learning algorithms for text categorization, namely a naïve Bayes approach and a relevance feedback method, with a word sense disambiguation strategy based exclusively on the lexical knowledge stored in the WordNet lexical database. Experiments carried out on a content-based extension of the EachMovie dataset show an improvement of the accuracy of sense-based profiles with respect to keyword-based ones, when coping with the task of classifying movies as interesting (or not) for the current user. An experimental session has been also performed in order to evaluate the proposed hybrid recommender system. The results highlight the improvement in the predictive accuracy of collaborative recommendations obtained by selecting like-minded users according to user profiles.     

融合信任因子的多样化电影推荐算法

传统的协同过滤算法过于依赖用户之间的评分,容易出现冷启动和数据稀疏性问题,同时推荐结果单一,针对以上问题,本文提出了一种融合信任因子的多样化电影推荐算法.首先对用户相似度计算方法进行改进,引入用户间信任度关系和属性特征信息.接着使用聚类方法把具有相同兴趣的用户划分在同一社群.最后在评分时综合考虑用户活跃度对电影的推荐度,引入惩罚因子,从而为目标用户提供个性化、多样化的电影推荐.实验结果表明,本文提出的算法在推荐精度和多样性指标上均有所提高,有较好的推荐效果.     

Threshold-Based Dynamic Replication in Large-Scale Video-on-Demand Systems

Recent advances in high speed networking technologies and video compression techniques have made Video-on-Demand (VOD) services feasible. A large-scale VOD system imposes a large demand on I/O bandwidth and storage resources, and therefore, parallel disks are typically used for providing VOD service. Although striping of movie data across a large number of disks can balance the utilization among these disks, such a striping technique can exhibit additional complexity, for instance, in data management, such as synchronization among disks during data delivery, as well as in supporting fault tolerant behavior. Therefore, it is more practical to limit the extent of data striping, for example, by arranging the disks in groups (or nodes) and then allowing intra-group (or intra-node) data striping only. With multiple striping groups, however, we may need to assign a movie to multiple nodes so as to satisfy the total demand of requests for that movie. Such an approach gives rise to several design issues, including: (1) what is the right number of copies of each movie we need so as to satisfy the demand and at the same time not waste storage capacity, (2) how to assign these movies to different nodes in the system, and (3) what are efficient approaches to altering the number of copies of each movie (and their placement) when the need for that arises. In this paper, we study an approach to dynamically reconfiguring the VOD system so as to alter the number of copies of each movie maintained on the server as the access demand for these movies fluctuates. We propose various approaches to addressing the above stated issues, which result in a VOD design that is adaptive to the changes in data access patterns. Performance evaluation is carried out to quantify the costs and the performance gains of these techniques.     

A Movie Recommendation System – An Application of Voting Theory in User Modeling

Our research agenda focuses on building software agents that can employ user modeling techniques to facilitate information access and management tasks. Personal assistant agents embody a clearly beneficial application of intelligent agent technology. A particular kind of assistant agents, recommender systems, can be used to recommend items of interest to users. To be successful, such systems should be able to model and reason with user preferences for items in the application domain. Our primary concern is to develop a reasoning procedure that can meaningfully and systematically tradeoff between user preferences. We have adapted mechanisms from voting theory that have desirable guarantees regarding the recommendations generated from stored preferences. To demonstrate the applicability of our technique, we have developed a movie recommender system that caters to the interests of users. We present issues and initial results based on experimental data of our research that employs voting theory for user modeling, focusing on issues that are especially important in the context of user modeling. We provide multiple query modalities by which the user can pose unconstrained, constrained, or instance-based queries. Our interactive agent learns a user model by gaining feedback aboutits recommended movies from the user. We also provide pro-active information gathering to make user interaction more rewarding. In the paper, we outline the current status of our implementation with particular emphasis on the mechanisms used to provide robust and effective recommendations.     

Exploiting character networks for movie summarization

Movie summarization focuses on providing as much information as possible for shorter movie clips while still keeping the content of the original movie and presenting a faster way for the audience to understand the movie. In this paper, we propose a novel method to summarize a movie based on character network analysis and the appearance of protagonist and main characters in the movie. Experiments were carried out for 2 movies (Titanic (1997) and Frozen (2013)) to show that our method outperforms conventional approaches in terms of the movie summarization rate.     

Entertainment recommender systems for group of users

Recommender systems are used to recommend potentially interesting items to users in different domains. Nowadays, there is a wide range of domains in which there is a need to offer recommendations to group of users instead of individual users. As a consequence, there is also a need to address the preferences of individual members of a group of users so as to provide suggestions for groups as a whole. Group recommender systems present a whole set of new challenges within the field of recommender systems. In this article, we present two expert recommender systems that suggest entertainment to groups of users. These systems, jMusicGroupRecommender and jMoviesGroupRecommender, suggest music and movies and utilize different methods for the generation of group recommendations: merging recommendations made for individuals, aggregation of individuals’ ratings, and construction of group preference models. We also describe the results obtained when comparing different group recommendation techniques in both domains.     

Embedded learning for computerized production of movie trailers

Movie trailers are usually extracted from the most exciting, interesting, or other noteworthy parts of the movies in order to attract the audience and persuade them to see the film. At present, hand-crafted movie trailers currently occupy almost all the filming market, which is costly and time-consuming. In this paper, we propose an embedded learning algorithm to generate movie trailers automatically without human interventions. Firstly, we use CNN to extract features of candidate frames from the film by a rank-tracing technique. Secondly, SURF algorithm is utilized to match the frames of the movie with the corresponding trailer, thus the labeled and unlabeled dataset are prepared. Thirdly, the mutual information theory is introduced into the embedded machine learning to formulate a new embedded classification algorithm and hence characterize similar key elements of the trailers. Finally, semi-supervised support vector machine is applied as the classifier to obtain the satisfactory key frames to produce the predicted trailers. By treating several famous movies and their manual handling trailers as the ground-truth, series of experiments are carried out, which indicate that our method is feasible and competitive, providing a good potential for promoting the rapid development of the film industry in terms of publicity, as well as providing users with possible solutions for filtering large amounts of Internet videos.     

Searching for Flash Movies on the Web: A Content and Context Based Framework

The phenomenal growth of online Flash movies in recent years has made Flash one of the most prevalent media formats on the Web. The retrieval and management issues of Flash, vital to the utilization of the enormous Flash resource, are unfortunately overlooked by the research community. This paper presents the first piece of work (to the best of our knowledge) in this domain by suggesting an integrated framework for the retrieval of Flash movies based on their content characteristics as well as contextual information. The proposed approach consists of two major components: (1) a content-based retrieval component, which explores the characteristics of Flash movie content at compositional and semantic levels; and (2) a context-based retrieval component, which explores the contextual information including the texts and hyperlinks surrounding the movies. An experimental Flash search engine system has been implemented to demonstrate the feasibility of the suggested framework. The work described in this paper was supported substantially by a grant (Project No. 7001457), and partially by another grant (Project No. 7001564), both from CityU of Hong Kong.     

Estimating global opinions by keeping users from fraud in online review systems

In this work, we focus on online review systems, in which users provide opinions about a set of entities (movies, restaurants, etc.) based on their experiences and in turn can check what others prefer. These systems have been proved to be sensitive to fraud and have shown some shortcomings as a result of capturing opinions through numerical ratings. Thus, supported by recent work on the field, we tackle the problem of fraud in such systems by designing a mechanism based on pairwise comparisons, coupled with an incentive policy attempting to foster the collection of majority opinions over individual experiences. As a result, we propose a new mechanism called iPWRM (incentive-based PWRM), where users are persuaded to reply honestly to pairwise queries based on opinion polls. The idea is: (1) to give a positive reward when all users agree in their reviews; (2) to give a positive reward when a user agrees the majority’s choice; and finally, (3) to give a low incentive—possibly null—when user’s review does not match the majority. Therefore, it is able (1) to overcome the bias introduced into reputation rankings by fraud reviews in ORSs, as well as (2) to mitigate potential biased problems derived from the use of numerical ratings. We exhaustively test the performance of the mechanism by using two different well-known existing datasets Flixster and HetRec2011—real world datasets on movie reviews, aiming to test the performance of the mechanism as well as the effectiveness and efficiency of iPWRM when fraud comes into play.