A cloud-based intelligent TV program recommendation system

In recent years, cloud computing technology has matured significantly, as has the development of digital TV services. This, therefore, has led to an increased demand for improved quality TV services. In this paper, cloud computing technology is used to build a program recommendation system for digital TV programs, and the Hadoop Fair Scheduler is utilized to improve processing performance. Historical data of watched TV programs are collected through an electronic program guide, and then processed using K-means clustering, term frequency/inverse document frequency and k-nearest neighbor algorithms, to obtain clusters of audience groups and to find popular TV programs for each cluster. The proposed system can process massive amounts of user data in real-time, and can easily be scaled up.     

Neural TV program recommendation with heterogeneous attention

Knowledge and Information Systems - TV program recommendation is very important to avoid confusing users with large amounts of information. The existing methods are mainly based on collaborative...     

Topic-tracking-based dynamic user modeling with TV recommendation applications

One of the challenging issues in TV recommendation applications based on implicit rating data is how to make robust recommendation for the users who irregularly watch TV programs and for the users who have their time-varying preferences on watching TV programs. To achieve the robust recommendation for such users, it is important to capture dynamic behaviors of user preference on watched TV programs over time. In this paper, we propose a topic tracking based dynamic user model (TDUM) that extends the previous multi-scale dynamic topic model (MDTM) by incorporating topic-tracking into dynamic user modeling. In the proposed TDUM, the prior of the current user preference is estimated as a weighted combination of the previously learned preferences of a TV user in multi-time spans where the optimal weight set is found in the sense of the evidence maximization of the Bayesian probability. So, the proposed TDUM supports the dynamics of public users’ preferences on TV programs for collaborative filtering based TV program recommendation and the highly ranked TV programs by similar watching taste user group (topic) can be traced with the same topic labels epoch by epoch. We also propose a rank model for TV program recommendation. In order to verify the effectiveness of the proposed TDUM and rank model, we use a real data set of the TV programs watched by 1,999 TV users for 7 months. The experiment results demonstrate that the proposed TDUM outperforms the Latent Dirichlet Allocation (LDA) model and the MDTM in log-likelihood for the topic modeling performance, and also shows its superiority compared to LDA, MDTM and Bayesian Personalized Rank Matrix Factorization (BPRMF) for TV program recommendation performance in terms of top-N precision-recall.     

Neural TV program recommendation with label and user dual attention

TV program recommendation is very important for users to find interesting TV programs and avoid confusing users with a lot of information. Currently, they are basically traditional collaborative filtering algorithms, which only recommend through the interactive data between users and programs ignoring the important value of some auxiliary information. In addition, the neural network method based on attention mechanism can well capture the relationship between program labels to obtain accurate program and user representations. In this paper, we propose a neural TV program recommendation with label and user dual attention (NPR-LUA), which can focus on auxiliary information in program and user modules. In the program encoder module, we learn the auxiliary information from program labels through neural networks and word attention to identify important program labels. In the user encoder module, we learn the user representation through the programs that the user watches and use personalized attention mechanism to distinguish the importance of programs for each user. Experiments on real data sets show that our method can effectively improve the effectiveness of TV program recommendations than other existing models.

     

Inferring competitive role patterns in reality TV show through nonverbal analysis

This paper introduces a new facet of social media, namely that depicting social interaction. More concretely, we address this problem from the perspective of nonverbal behavior-based analysis of competitive meetings. For our study, we made use of “The Apprentice” reality TV show, which features a competition for a real, highly paid corporate job. Our analysis is centered around two tasks regarding a person’s role in a meeting: predicting the person with the highest status, and predicting the fired candidates. We address this problem by adopting both supervised and unsupervised strategies. The current study was carried out using nonverbal audio cues. Our approach is based only on the nonverbal interaction dynamics during the meeting without relying on the spoken words. The analysis is based on two types of data: individual and relational measures. Results obtained from the analysis of a full season of the show are promising (up to 85.7% of accuracy in the first case and up to 92.8% in the second case). Our approach has been conveniently compared with the Influence Model, demonstrating its superiority.     

A location-aware multicasting protocol for Bluetooth Location Networks

Bluetooth Location Network (BLN) is a Bluetooth radio network that is composed of some mobile Bluetooth devices and static Bluetooth units, and is established at the system initialization to form a spontaneous network topology. In a BLN, a multicast service is defined as the periodical delivering of messages from a Service Server to a set of mobile devices which are the multicast members predefined by the Service Server. Several multicast protocols have been proposed for the Ad-Hoc networks, but they create an inefficient multicast tree for the BLN due to the existing differences in the radio characteristics between Ad-Hoc and Bluetooth radio networks. The present paper analyzes these differences and proposes a novel multicasting protocol for constructing an efficient multicast tree in a BLN. The proposed protocol constructs a multicast tree with good features which include the shortest path, a higher degree of path sharing, and fewer forwarding nodes. Simulation results reveal that the proposed multicast protocol outperforms the existing multicast protocols in the BLN.     

Georoy: A location-aware enhancement to Viceroy peer-to-peer algorithm

The success of experiences such as Seattle and Houston Wireless has attracted the attention on the so called wireless mesh community networks. These are wireless multihop networks spontaneously deployed by users willing to share communication resources. Due to the community spirit characterizing such networks, it is likely that users will be willing to share other resources besides communication resources, such as data, images, music, movies, disk quotas for distributed backup, and so on. To support resource exchange in these wireless mesh community networks, algorithms for efficient retrieval of information are required. In this paper we introduce Georoy, an algorithm for the efficient retrieval of the information on resource location based on the Viceroy peer-to-peer algorithm. Differently from Viceroy, Georoy exploits the capability of setting and managing a direct mapping between the resource ID and the node which maintains information about its location so as to speed up the search process. Simulation results show that Georoy enables efficient and scalable search of resources and can be successfully used in wireless mesh community networks.     

A novel stock recommendation system using Guba sentiment analysis

Investment recommendation has been one of the hottest topics in the finance area which can help investors to get more profits and to avoid loss. Existing recommendation systems mostly depend on analysis of trading data and company profit prediction. Though many works show that there is a positive correlation between investors’ sentiment and the finance market trends, few recommendation theories have been built based on sentiment. The primary reason is the difficulty to measure investors’ sentiment. In this work, a novel stock recommendation system is developed based on a proposed theory concerning the correlation between Guba-based sentiment of the retail investors and the stock market trends in China. To verify four hypotheses of the theory, a novel method is proposed to measure the investors’ sentiment by exploiting the large volumes of emotion enriched texts posted in Guba, which is online social platform for individual investors to share news and opinions concerning their favorite stocks. Results show the correctness of the proposed theory: (1) there is a positive correlation between Guba-based sentiment and the stock market trends; 2) the higher the post volumes and agreement, more proficiency the bullishness would be; and (3) a long-lasting negative Guba-based sentiment indicates the arrival of the bear market. The proposed recommendation system consists of three criteria accordingly to ensure the portfolio to meet requirements of the theory. Finally, experiments are implemented using the real data of Chinese stock market from March 2009 to March 2016 and the results show the effectiveness of the proposed system in recommending lucrative stocks and the theoretical cumulate profit is about eight times of the CSI300 in the period.     

DFIAM: deep factorization integrated attention mechanism for smart TV recommendation

World Wide Web - Users are frequently overwhelmed by their uninterested programs due to the development of smart TV and the excessive number of programs. For addressing this issue, various...     

Automatic and personalized recommendation of TV program contents using sequential pattern mining for smart TV user interaction

Due to the excessive number of TV program contents available at user’s side, efficient access to the preferred TV program content becomes a critical issue for smart TV user interaction. In this paper, we propose an automatic recommendation scheme of TV program contents in sequence using sequential pattern mining (SPM). Motivation of sequential TV program recommendation is based on TV viewer’s behaviors for watching multiple TV program contents in a row. A sequence of TV program contents for recommendation to a target user is constructed based on the features such as an occurrence and net occurrence of frequently watched TV program contents from the similar user group to which the target user belongs. Three types of SPM methods are presented—offline, online and hybrid SPM. To extract sequential patterns of preferably watched TV program contents, we propose a preference weighted normalized modified retrieval rank (PW-NMRR) metric for similar user clustering. In the offline SPM method, we effectively construct the sequential patterns for recommendation using a projection method, which yields good performance for relatively longer sequential patterns. The online SPM method mines sequential patterns online by effectively reflecting the recent preference characteristics of users for TV program contents, which is effective for short-sequence recommendation. The hybrid SPM method combines the offline and online SPM methods. The maximum precisions of 0.877, 0.793 and 0.619 for length-1, -2 and -3 sequence recommendations are obtained from the online, hybrid and offline SPM methods, respectively.     

A soft computing based location-aware access control for smart buildings

The evolution of wireless communications and pervasive computing is transforming current physical spaces into real smart environments. These emerging scenarios are expected to be composed by a potentially huge amount of heterogeneous smart objects which can be remotely accessed by users via their mobile devices anytime, anywhere. In this paper, we propose a distributed location-aware access control mechanism and its application in the smart building context. Our approach is based on an access control engine embedded into smart objects, which are responsible to make authorization decisions by considering both user location data and access credentials. User location data are estimated using a novel indoor localization system based on magnetic field data sent by user through her personal phone. This localization system implements a combination of soft computing techniques over the data collected by smartphones. Therefore, our location-aware access control mechanism does not require any intermediate entity, providing the benefits of a decentralized approach for smart environments. From the results obtained, we can consider our proposal as a promising approach to tackle the challenging security requirements of typical pervasive environments.     

一种基于用户兴趣分析的协同过滤推荐算法

传统的协同过滤推荐算法以用户对所有物品的评分向量作为计算用户相似度的依据,没有考虑到物品属性对用户兴趣的反映。为此,提出一种新的改进的相似度计算方法,引入了"用户兴趣分布矩阵"的定义,设计了启发式的评分预测方式,即根据兴趣相似度选出TOP-K用户之后,以用户标记的物品数量作为该用户的权重来预测评分。在Movielens数据集上的测试结果表明,改进后的算法相比传统的算法在平均绝对误差(MAE)上降低了7.3%。     

A comprehensive analysis on movie recommendation system employing collaborative filtering

Multimedia Tools and Applications - Collaborative Filtering (CF) is one of the most extensively used technologies for Recommender Systems (RS), it shows an improved intelligent searching mechanism...     

Automatic metadata expansion and indirect collaborative filtering for TV program recommendation system

TV Program recommendation is a good example of a novel application of networked appliances using personalization technologies. The aim of this paper is to propose methods to improve the accuracy of TV program recommendation. Automatic metadata expansion (AME) is a method to enhance TV program metadata from electronic program guide (EPG) data, and indirect collaborative filtering (ICF) is a method to recommend non-persistent items such as TV programs based on the preferences of other members in a community. In this paper, the effectiveness of these methods is confirmed through experiments. This online TV recommendation system is currently being used by 230,000 members in Japan. The result of the actual operation is also discussed.     

Web video thumbnail recommendation with content-aware analysis and query-sensitive matching

In this paper, a unified and adaptive web video thumbnail recommendation framework is proposed, which recommends thumbnails both for video owners and browsers on the basis of image quality assessment, image accessibility analysis, video content representativeness analysis and query-sensitive matching. At the very start, video shot detection is performed and the highest image quality video frame is extracted as the key frame for each shot on the basis of our proposed image quality assessment method. These key frames are utilized as the thumbnail candidates for the following processes. In the image quality assessment, the normalized variance autofocusing function is employed to evaluate the image blur and ensures that the selected video thumbnail candidates are clear and have high image quality. For accessibility analysis, color moment, visual salience and texture are used with a support vector regression model to predict the candidates’ accessibility score, which ensures that the recommended thumbnail’s ROIs are big enough and it is very accessible for users. For content representativeness analysis, the mutual reinforcement algorithm is adopted in the entire video to obtain the candidates’ representativeness score, which ensures that the final thumbnail is representative enough for users to catch the main video contents at a glance. Considering browsers’ query intent, a relevant model is designed to recommend more personalized thumbnails for certain browsers. Finally, by flexibly fusing the above analysis results, the final adaptive recommendation work is accomplished. Experimental results and subjective evaluations demonstrate the effectiveness of the proposed approach. Compared with the existing web video thumbnail generation methods, the thumbnails for video owners not only reflect the contents of the video better, but also make users feel more comfortable. The thumbnails for video browsers directly reflect their preference, which greatly enhances their user experience.     

Empirical analysis of session-based recommendation algorithms

Recommender systems are tools that support online users by pointing them to potential items of interest in situations of information overload. In recent years, the class of session-based recommendation algorithms received more attention in the research literature. These algorithms base their recommendations solely on the observed interactions with the user in an ongoing session and do not require the existence of long-term preference profiles. Most recently, a number of deep learning-based (“neural”) approaches to session-based recommendations have been proposed. However, previous research indicates that today’s complex neural recommendation methods are not always better than comparably simple algorithms in terms of prediction accuracy. With this work, our goal is to shed light on the state of the art in the area of session-based recommendation and on the progress that is made with neural approaches. For this purpose, we compare twelve algorithmic approaches, among them six recent neural methods, under identical conditions on various datasets. We find that the progress in terms of prediction accuracy that is achieved with neural methods is still limited. In most cases, our experiments show that simple heuristic methods based on nearest-neighbors schemes are preferable over conceptually and computationally more complex methods. Observations from a user study furthermore indicate that recommendations based on heuristic methods were also well accepted by the study participants. To support future progress and reproducibility in this area, we publicly share the session-rec evaluation framework that was used in our research.

     

LACO: A location-aware cooperative query system for securely personalized services

Location-aware computing technology becomes promising for pervasive personalization services which run anytime, anywhere, and on any device. These services should be based on contextual queries that are provided in a fast and flexible manner. To do so, cooperative query answering may be useful to support query relaxation and to provide both approximate matches as well as exact matches. To facilitate query relaxation, a knowledge representation framework has been widely adopted which accommodates semantic relationships or distance metrics to represent similarities among data values. However, research shows few legacy cooperative query mechanisms that consider location-awareness. Hence, the purpose of this paper is to propose a securely personalized location-aware cooperative query that supports conceptual distance metric among data values, while considering privacy concerns around user context awareness. To show the feasibility of the methodology proposed in this paper, we have implemented a prototype system, LACO, in the area of site search in an actual large-scale shopping mall.