Mining interests for user profiling in electronic conversations

The increasing amount of Web-based tasks is currently requiring personalization strategies to improve the user experience. However, building user profiles is a hard task, since users do not usually give explicit information about their interests. Therefore, interests must be mined implicitly from electronic sources, such as chat and discussion forums. In this work, we present a novel method for topic detection from online informal conversations. Our approach combines: (i) Wikipedia, an extensive source of knowledge, (ii) a concept association strategy, and (iii) a variety of text-mining techniques, such as POS tagging and named entities recognition. We performed a comparative evaluation procedure for searching the optimal combination of techniques, achieving encouraging results.     

Contextualizing and capturing individual user interactions in shared iTV environments

Multimedia Tools and Applications - Advances in Interactive TV (iTV) technology have enabled users to actively interact with the TV instead of just passively watching it. Associating the individual...     

Inferring user interests in microblogging social networks: a survey

With the growing popularity of microblogging services such as Twitter in recent years, an increasing number of users are using these services in their daily lives. The huge volume of information generated by users raises new opportunities in various applications and areas. Inferring user interests plays a significant role in providing personalized recommendations on microblogging services, and also on third-party applications providing social logins via these services, especially in cold-start situations. In this survey, we review user modeling strategies with respect to inferring user interests from previous studies. To this end, we focus on four dimensions of inferring user interest profiles: (1) data collection, (2) representation of user interest profiles, (3) construction and enhancement of user interest profiles, and (4) the evaluation of the constructed profiles. Through this survey, we aim to provide an overview of state-of-the-art user modeling strategies for inferring user interest profiles on microblogging social networks with respect to the four dimensions. For each dimension, we review and summarize previous studies based on specified criteria. Finally, we discuss some challenges and opportunities for future work in this research domain.     

Modeling user interests by conceptual clustering

As more information becomes available on the Web, there has been a crescent interest in effective personalization techniques. Personal agents providing assistance based on the content of Web documents and the user interests emerged as a viable alternative to this problem. Provided that these agents rely on having knowledge about users contained into user profiles, i.e., models of user preferences and interests gathered by observation of user behavior, the capacity of acquiring and modeling user interest categories has become a critical component in personal agent design. User profiles have to summarize categories corresponding to diverse user information interests at different levels of abstraction in order to allow agents to decide on the relevance of new pieces of information. In accomplishing this goal, document clustering offers the advantage that an a priori knowledge of categories is not needed, therefore the categorization is completely unsupervised. In this paper we present a document clustering algorithm, named WebDCC (Web Document Conceptual Clustering), that carries out incremental, unsupervised concept learning over Web documents in order to acquire user profiles. Unlike most user profiling approaches, this algorithm offers comprehensible clustering solutions that can be easily interpreted and explored by both users and other agents. By extracting semantics from Web pages, this algorithm also produces intermediate results that can be finally integrated in a machine-understandable format such as an ontology. Empirical results of using this algorithm in the context of an intelligent Web search agent proved it can reach high levels of accuracy in suggesting Web pages.     

Semantic user profiling techniques for personalised multimedia recommendation

Due to the explosion of news materials available through broadcast and other channels, there is an increasing need for personalised news video retrieval. In this work, we introduce a semantic-based user modelling technique to capture users’ evolving information needs. Our approach exploits implicit user interaction to capture long-term user interests in a profile. The organised interests are used to retrieve and recommend news stories to the users. In this paper, we exploit the Linked Open Data Cloud to identify similar news stories that match the users’ interest. We evaluate various recommendation parameters by introducing a simulation-based evaluation scheme.     

在线用户兴趣多样性的实证研究

在线用户的群体兴趣对于分析在线社会网络以及个性化推荐至关重要。研究的目的是引入信息熵这一指标来准确度量用户兴趣的多样性。分别在电影网站MovieLens和音乐网站Last．FM数据上进行实证分析,即统计度相同的用户所选产品的信息熵值。MovieLens的结果表明,随着用户度的增加,熵值出现先上升后下降的趋势,即度小的用户和度大的用户的兴趣比较专一,而一般用户的兴趣较为多样;而Last．FM的结果表明,度小用户的兴趣非常多样,但随着用户听过的音乐数量越多,兴趣越明确。通过建立随机模型与实证结果进行比较,可以发现绝大多数用户在真实数据集上的兴趣的多样性比随机情况要大,可见用户的兴趣对用户行为模式的影响显著。     

Modeling user multiple interests by an improved GCS approach

User interest profile is the crucial component of most personalized recommender systems. The diversity and time-dependent evolving nature of user interests are creating difficulties in constructing and maintaining a sound user profile. This paper presents a simple but effective model, by using improved growing cell structures (GCS), to address this problem. The GCS is a kind of self-organizing map neural network with changeable network structure. By virtue of the clustering and structure adaptation capability of GCS, the proposed model maps the problem of learning and keeping track of user interests into a clustering and cluster-maintaining problem. Each cluster found by GCS represents an interest category of a user and the cluster maintaining, including cluster addition and deletion, corresponds to the addition of user's new interests and the removal of user's old interests. The proposed model has been validated by a set of experiments performed on a benchmark dataset. Results from experiments show that our model provides reasonable performance and high adaptability for learning user multiple interests and their changes.     

Providing user context for mobile and social networking applications

The processing capabilities of mobile devices coupled with portable and wearable sensors provide the basis for new context-aware services and applications tailored to the user environment and daily activities. In this article, we describe the approach developed within the UPCASE project, which makes use of sensors available in the mobile device as well as sensors externally connected via Bluetooth to provide user contexts. We describe the system architecture from sensor data acquisition to feature extraction, context inference and the publication of context information in web-centered servers that support well-known social networking services. In the current prototype, context inference is based on decision trees to learn and to identify contexts dynamically at run-time, but the middleware allows the integration of different inference engines if necessary. Experimental results in a real-world setting suggest that the proposed solution is a promising approach to provide user context to local mobile applications as well as to network-level applications such as social networking services.     

Tag-based user modeling for social multi-device adaptive guides

This paper aims to demonstrate that the principles of adaptation and user modeling, especially social annotation, can be integrated fruitfully with those of the web 2.0 paradigm and thereby enhance in the domain of cultural heritage. We propose a framework for improving recommender systems through exploiting the users tagging activity. We maintain that web 2.0’s participative features can be exploited by adaptive web-based systems in order to enrich and extend the user model, improve social navigation and enrich information from a bottom-up perspective. Thus our approach stresses social annotation as a new and powerful kind of feedback and as a way to infer knowledge about users. The prototype implementation of our framework in the domain of cultural heritage is named iCITY. It is serving to demonstrate the validity of our approach and to highlight the benefits of this approach specifically for cultural heritage. iCITY is an adaptive, social, multi-device recommender guide that provides information about the cultural resources and events promoting the cultural heritage in the city of Torino. Our paper first describes this system and then discusses the results of a set of evaluations that were carried out at different stages of the systems development and aimed at validating the framework and implementation of this specific prototype. In particular, we carried out a heuristic evaluation and two sets of usability tests, aimed at checking the usability of the user interface, specifically of the adaptive behavior of the system. Moreover, we conducted evaluations aimed at investigating the role of tags in the definition of the user model and the impact of tags on the accuracy of recommendations. Our results are encouraging.

基于社交媒体用户评论和关注度的电影票房预测模型

通过研究电影票房与社交媒体用户行为的关系,揭示在线口碑(word-of-mouth)对业绩表现的作用。与之前的研究不同,将社交媒体用户评论、用户关注等用户行为数据作为内生变量进行研究,认为用户行为既影响业绩,又被业绩影响。首先,以电影产业为研究对象,分析了每周票房与用户评论、用户评分、用户关注度等之间的关系,通过样板(Panel)数据分析,构建了电影票房预测模型。接着,将票房作为自变量,分析了作为在线口碑表现形式的用户评论、用户关注度与票房的关系。最后,分析了在线口碑自身的特点,得出了多个有意义的结论,如用户评分仅仅是票房收入的反映,其本身并不显著影响票房。本研究具有良好的理论价值和实践意义。     

基于隐半马尔可夫模型的用户兴趣特征提取

针对网络用户兴趣行为特征的抽取,提出了一种基于隐半马尔可夫模型的用户兴趣特征提取模型,通过用状态驻留时间的概率来控制用户浏览行为,使描述兴趣特征的隐状态和时间的相关性更紧密地结合起来,并且根据隐半马尔可夫模型可以产生多观察值序列的特性,把文本信息划分成多个文本块子区域,使每个子区域的特征和其中一个观察值序列对应起来。实验结果表明,利用隐半马尔可夫模型进行特征提取比HMM方法有更高的准确率和召回率。     

Keyword clustering for user interest profiling refinement within paper recommender systems

To refine user interest profiling, this paper focuses on extending scientific subject ontology via keyword clustering and on improving the accuracy and effectiveness of recommendation of the electronic academic publications in online services. A clustering approach is proposed for domain keywords for the purpose of the subject ontology extension. Based on the keyword clusters, the construction of user interest profiles is presented on a rather fine granularity level. In the construction of user interest profiles, we apply two types of interest profiles: explicit profiles and implicit profiles. The explicit profiles are obtained by relating users’ interest-topic relevance factors to users’ interest measurements of these topics computed by a conventional ontology-based method, and the implicit profiles are acquired on the basis of the correlative relationships among the topic nodes in topic network graphs. Three experiments are conducted which reveal that the uses of the subject ontology extension approach as well as the two types of interest profiles satisfyingly contribute to an improvement in the accuracy of recommendation.     

Privacy policies for shared content in social network sites

Social networking is one of the major technological phenomena of the Web 2.0, with hundreds of millions of subscribed users. Social networks enable a form of self-expression for users and help them to socialize and share content with other users. In spite of the fact that content sharing represents one of the prominent features of existing Social network sites, they do not provide any mechanisms for collective management of privacy settings for shared content. In this paper, using game theory, we model the problem of collective enforcement of privacy policies on shared data. In particular, we propose a solution that offers automated ways to share images based on an extended notion of content ownership. Building upon the Clarke-Tax mechanism, we describe a simple mechanism that promotes truthfulness and that rewards users who promote co-ownership. Our approach enables social network users to compose friendship based policies based on distances from an agreed upon central user selected using several social networks metrics. We integrate our design with inference techniques that free the users from the burden of manually selecting privacy preferences for each picture. To the best of our knowledge, this is the first time such a privacy protection mechanism for social networking has been proposed. We also extend our mechanism so as to support collective enforcement across multiple social network sites. In the paper, we also show a proof-of-concept application, which we implemented in the context of Facebook, one of today’s most popular social networks. Through our implementation, we show the feasibility of such approach and show that it can be implemented with a minimal increase in overhead to end-users. We complete our analysis by conducting a user study to investigate users’ understanding of co-ownership, usefulness and understanding of our approach. Users responded favorably to the approach, indicating a general understanding of co-ownership and the auction, and found the approach to be both useful and fair.     

Exploring convolutional neural networks and topic models for user profiling from drug reviews

Multimedia Tools and Applications - Pharmacovigilance, and generally applications of natural language processing models to healthcare, have attracted growing attention over the recent years. In...     

Home location profiling for users in social media

In this paper, we focus on the problem of estimating the home locations of users in the Twitter network. We propose a Social Tie Factor Graph (STFG) model to estimate a Twitter user's city-level location based on the user's following network, user-centric data, and tie strength. In STFG, relationships between users and locations are modeled as nodes, while attributes and correlations are modeled as factors. An efficient algorithm is proposed to learn model parameters and predict unknown relationships. We evaluate our proposed method by investigating Twitter networks. The experimental results demonstrate that our proposed method significantly outperforms several state-of-the-art methods.