A time-aware spatio-textual recommender system

Location-Based Social Networks (LBSNs) allow users to post ratings and reviews and to notify friends of these posts. Several models have been proposed for Point-of-Interest (POI) recommendation that use explicit (i.e. ratings, comments) or implicit (i.e. statistical scores, views, and user influence) information. However the models so far fail to capture sufficiently user preferences as they change spatially and temporally. We argue that time is a crucial factor because user check-in behavior might be periodic and time dependent, e.g. check-in near work in the mornings and check-in close to home in the evenings. In this paper, we present two novel unified models that provide review and POI recommendations and consider simultaneously the spatial, textual and temporal factors. In particular, the first model provides review recommendations by incorporating into the same unified framework the spatial influence of the users’ reviews and the textual influence of the reviews. The second model provides POI recommendations by combining the spatial influence of the users’ check-in history and the social influence of the users’ reviews into another unified framework. Furthermore, for both models we consider the temporal dimension and measure the impact of time on various time intervals. We evaluate the performance of our models against 10 other methods in terms of precision and recall. The results indicate that our models outperform the other methods.     

Viral marketing for dedicated customers

Viral marketing has attracted considerable concerns in recent years due to its novel idea of leveraging the social network to propagate the awareness of products. Specifically, viral marketing first targets a limited number of users (seeds) in the social network by providing incentives, and these targeted users would then initiate the process of awareness spread by propagating the information to their friends via their social relationships. Extensive studies have been conducted for maximizing the awareness spread given the number of seeds (the Influence Maximization problem). However, all of them fail to consider the common scenario of viral marketing where companies hope to use as few seeds as possible yet influencing at least a certain number of users. In this paper, we propose a new problem, called J-MIN-Seed, whose objective is to minimize the number of seeds while at least J users are influenced. J-MIN-Seed, unfortunately, is NP-hard. Therefore, we develop an approximate algorithm which can provide error guarantees for J-MIN-Seed. We also observe that all existing studies on viral marketing assume that all users in the social network are of interest for the product being promoted (i.e., all users are potential consumers of the product), which, however, is not always true. Motivated by this phenomenon, we propose a new paradigm of viral marketing where the company can specify which types of users in the social network are of interest when promoting a specific product. Under this new paradigm, we re-define our J-MIN-Seed problem as well as the Influence Maximization problem and design some algorithms with provable error guarantees for the new problems. We conducted extensive experiments on real social networks which verified the effectiveness of our algorithms.     

A context-aware recommender method based on text and opinion mining

A recommender system is an information filtering technology that can be used to recommend items that may be of interest to users. Additionally, there are the context-aware recommender systems that consider contextual information to generate the recommendations. Reviews can provide relevant information that can be used by recommender systems, including contextual and opinion information. In a previous work, we proposed a context-aware recommendation method based on text mining (CARM-TM). The method includes two techniques to extract context from reviews: CIET.5_embed, a technique based on word embeddings; and RulesContext, a technique based on association rules. In this work, we have extended our previous method by including CEOM, a new technique which extracts context by using aspect-based opinions. We call our extension of CARM-TOM (context-aware recommendation method based on text and opinion mining). To generate recommendations, our method makes use of the CAMF algorithm, a context-aware recommender based on matrix factorization. To evaluate CARM-TOM, we ran an extensive set of experiments in a dataset about restaurants, comparing CARM-TOM against the MF algorithm, an uncontextual recommender system based on matrix factorization; and against a context extraction method proposed in literature. The empirical results strongly indicate that our method is able to improve a context-aware recommender system.     

Meme ranking to maximize posts virality in microblogging platforms

Microblogging is a modern communication paradigm in which users post bits of information, or “memes” as we call them, that are brief text updates or micromedia such as photos, video or audio clips. Once a user post a meme, it become visible to the user community. When a user finds a meme of another user interesting, she can eventually repost it, thus allowing memes to propagate virally trough the social network. In this paper we introduce the meme ranking problem, as the problem of selecting which k memes (among the ones posted by their contacts) to show to users when they log into the system. The objective is to maximize the overall activity of the network, that is, the total number of reposts that occur. We deeply characterize the problem showing that not only exact solutions are unfeasible, but also approximated solutions are prohibitive to be adopted in an on-line setting. Therefore we devise a set of heuristics and we compare them trough an extensive simulation based on the real-world Yahoo! Meme social graph, using parameters learnt from real logs of meme propagations. Our experimentation demonstrates the effectiveness and feasibility of these methods.     

Mutual development in mass collaboration: Identifying interaction patterns in customer-initiated software product development

In this paper we investigate computer-supported collaborative learning (CSCL) and innovation in a large-scale distributed setting. Get Satisfaction (GS), a social media platform for involving customers in product development activities, is our case study. In order to identify how end users contribute to product development, we researched the interactions between end users, champions, and professional developers in this online community as they jointly constructed a shared artifact (a web application). We collected publicly available platform interaction data over a six-month period (N = 229 users). The methods we employed are social network analysis (SNA) and interaction analysis (IA), which we combined in a mixed-methods design. At the network level, we identified key actors according to centrality measures. At the interaction level, we zoomed in on specific interactions. We propose a model of mass collaboration in terms of four interaction patterns: 1) gatekeeping, control of excessive information sharing, 2) bridge building, spreading information across groups in the network, 3) general development, allowing professional developers to create new software functionality and update existing software, and 4) user-user collaboration, facilitating non-centrally organized development activities, ranging from feature requests to local development. We discuss our findings and compare them with related research.     

CSLabel: An Approach for Labelling Mobile App Reviews

Mobile apps (applications) have become a popular form of software, and the app reviews by users have become an important feedback resource. Users may raise some issues in their reviews when they use apps, such as a functional bug, a network lag, or a request for a feature. Understanding these issues can help developers to focus on users’ concerns, and help users to evaluate similar apps for download or purchase. However, we do not know which types of issues are raised in a review. Moreover, the amount of user reviews is huge and the nature of the reviews’ text is unstructured and informal. In this paper, we analyze 3 902 user reviews from 11 mobile apps in a Chinese app store — 360 Mobile Assistant, and uncover 17 issue types. Then, we propose an approach CSLabel that can label user reviews based on the raised issue types. CSLabel uses a cost-sensitive learning method to mitigate the effects of the imbalanced data, and optimizes the setting of the support vector machine (SVM) classifier’s kernel function. Results show that CSLabel can correctly label reviews with the precision of 66.5%, the recall of 69.8%, and the F₁ measure of 69.8%. In comparison with the state-of-the-art approach, CSLabel improves the precision by 14%, the recall by 30%, the F₁ measure by 22%. Finally, we apply our approach to two real scenarios: 1) we provide an overview of 1 076 786 user reviews from 1 100 apps in the 360 Mobile Assistant and 2) we find that some issue types have a negative correlation with users’ evaluation of apps.     

An architecture and functional description to integrate social behaviour knowledge into group recommender systems

In this paper we consider the research challenges of generating a set of recommendations that will satisfy a group of users with potentially competing interests. We review different ways of combining the preferences of different users and propose an approach that takes into account the social behaviour within a group. Our method, named delegation-based prediction method, includes an analysis of the group characteristics, such as size, structure, personality of its members in conflict situations, and trust between group members. A key element in this paper is the use of social information available in the Web to make enhanced recommendations to groups. We propose a generic architecture named arise (Architecture for Recommendations Including Social Elements) and describe, as a case study, our Facebook application HappyMovie: a group recommender system that is designed to provide assistance to a group of friends that might be selecting which movie to watch on a cinema outing. We evaluate the performance (compared with the real group decision) of different recommenders that use increasing levels of social behaviour knowledge.     

Web crawling and filtering for on-line auctions from a social network perspective

The on-line auction is one of the most successful types of electronic marketplace and has been the subject of many academic studies. In recent years, empirical research on on-line auctions has been flourishing because of the availability of large amounts of high-quality bid data from on-line auction sites. However, the increasingly large volumes of bid data have made data collection ever more complex and time consuming, and there are no effective resources that can adequately support this work. So this study focuses on the parallel crawling and filtering of on-line auctions from the social network perspective to help researchers collect and analyze auction data more effectively. The issues raised in this study include parallel crawling architecture, crawling strategies, content filtering strategies, prototype system implementation, and a pilot test of social network analysis. Finally we conduct an empirical experiment on eBay US and Ruten Taiwan to evaluate the performance of our crawling architecture and to understand auction customers?? bidding behavior characteristics. The results of this study show that our parallel crawling and filtering methods are able to work in the real world, and are significantly more effective than manual web crawling. The collected data are useful for drawing social network maps and analyzing bidding problems.     

Boosting social collaborations based on contextual synchronization: An empirical study

Supporting context-based collaboration among online users is an important issue to computer-mediated collaboration to fulfill specified tasks. However, several problems make it difficult to be aware of the context. The context of the user task can be (i) dynamic (i.e., changing over time), and (ii) mixed with multiple sub-contexts together. We propose a novel ontology-based platform to overcome these problems. It finds the most relevant users from a given social network, taking into account two types of context (i.e., personal and group contexts) and matching them. By measuring similarities between the personal contexts, we can dynamically organize a number of communities, so that users can be contextually synchronized. Individual users can be involved in complex collaborations related to multiple semantics. This paper demonstrates and discusses how the proposed context synchronization process is able to boost social collaborations. We show the experimental results collected from a collaborative information searching system. The main empirical issues in this work are (i) setting thresholds, (ii) searching performance, and (iii) scalability testing.     

Extracting user web browsing patterns from non-content network traces: The online advertising case study

Online advertising is a rapidly growing industry currently dominated by the search engine ’giant’ Google. In an attempt to tap into this huge market, Internet Service Providers (ISPs) started deploying deep packet inspection techniques to track and collect user browsing behavior. However, these providers have the fear that such techniques violate wiretap laws that explicitly prevent intercepting the contents of communication without gaining consent from consumers. In this paper, we explore how it is possible for ISPs to extract user browsing patterns without inspecting contents of communication.Our contributions are threefold. First, we develop a methodology and implement a system that is capable of extracting web browsing features from stored non-content based network traces, which could be legally shared. When such browsing features are correlated with information collected by independently crawling the Web, it becomes possible to recover the actual web pages accessed by clients. Second, we evaluate our system on the Internet and check that it can successfully recover user browsing patterns with high accuracy.     

Peri-Watchdog: Hunting for hidden botnets in the periphery of online social networks

In order to evade detection of ever-improving defense techniques, modern botnet masters are constantly looking for new communication platforms for delivering C&C (Command and Control) information. Attracting their attention is the emergence of online social networks such as Twitter, as the information dissemination mechanism provided by these networks can naturally be exploited for spreading botnet C&C information, and the enormous amount of normal communications co-existing in these networks makes it a daunting task to tease out botnet C&C messages.Against this backdrop, we explore graph-theoretic techniques that aid effective monitoring of potential botnet activities in large open online social networks. Our work is based on extensive analysis of a Twitter dataset that contains more than 40 million users and 1.4 billion following relationships, and mine patterns from the Twitter network structure that can be leveraged for improving efficiency of botnet monitoring. Our analysis reveals that the static Twitter topology contains a small-sized core sugraph, after removing which, the Twitter network breaks down into small connected components, each of which can be handily monitored for potential botnet activities. Based on this observation, we propose a method called Peri-Watchdog, which computes the core of a large online social network and derives the set of nodes that are likely to pass botnet C&C information in the periphery of online social network. We analyze the time complexity of Peri-Watchdog under its normal operations. We further apply Peri-Watchdog on the Twitter graph injected with synthetic botnet structures and investigate the effectiveness of Peri-Watchdog in detecting potential C&C information from these botnets.To verify whether patterns observed from the static Twitter graph are common to other online social networks, we analyze another online social network dataset, BrightKite, which contains evolution of social graphs formed by its users in half a year. We show not only that there exists a similarly relatively small core in the BrightKite network, but also this core remains stable over the course of BrightKite evolution. We also find that to accommodate the dynamic growth of BrightKite, the core has to be updated about every 18 days under a constrained monitoring capacity.     

Focused crawling: a new approach to topic-specific Web resource discovery

The rapid growth of the World-Wide Web poses unprecedented scaling challenges for general-purpose crawlers and search engines. In this paper we describe a new hypertext resource discovery system called a Focused Crawler. The goal of a focused crawler is to selectively seek out pages that are relevant to a pre-defined set of topics. The topics are specified not using keywords, but using exemplary documents. Rather than collecting and indexing all accessible Web documents to be able to answer all possible ad-hoc queries, a focused crawler analyzes its crawl boundary to find the links that are likely to be most relevant for the crawl, and avoids irrelevant regions of the Web. This leads to significant savings in hardware and network resources, and helps keep the crawl more up-to-date.To achieve such goal-directed crawling, we designed two hypertext mining programs that guide our crawler: a classifier that evaluates the relevance of a hypertext document with respect to the focus topics, and a distiller that identifies hypertext nodes that are great access points to many relevant pages within a few links. We report on extensive focused-crawling experiments using several topics at different levels of specificity. Focused crawling acquires relevant pages steadily while standard crawling quickly loses its way, even though they are started from the same root set. Focused crawling is robust against large perturbations in the starting set of URLs. It discovers largely overlapping sets of resources in spite of these perturbations. It is also capable of exploring out and discovering valuable resources that are dozens of links away from the start set, while carefully pruning the millions of pages that may lie within this same radius. Our anecdotes suggest that focused crawling is very effective for building high-quality collections of Web documents on specific topics, using modest desktop hardware.     

Social welfare maximization in participatory smartphone sensing

Participatory smartphone sensing has lately become more and more popular as a new paradigm for performing large-scale sensing, in which each smartphone contributes its sensed data for a collaborative sensing application. Most existing studies consider that smartphone users are strictly strategic and completely rational, which try to maximize their own payoffs. A number of incentive mechanisms are designed to encourage smartphone users to participate, which can achieve only suboptimal system performance. However, few existing studies can maximize a system-wide objective which takes both the platform and smartphone users into account. This paper focuses on the crucial problem of maximizing the system-wide performance or social welfare for a participatory smartphone sensing system. There are two great challenges. First, the social welfare maximization cannot be realized on the platform side because the cost of each user is private and unknown to the platform in reality. Second, the participatory sensing system is a large-scale real-time system due to the huge number of smartphone users who are geo-distributed in the whole world. A price-based decomposition framework is proposed in our previous work (Liu and Zhu, 2013), in which the platform provides a unit price for the sensing time spent by each user and the users return the sensing time via maximizing the monetary reward. This pricing framework is an effective incentive mechanism as users are motivated to participate for monetary rewards from the platform. In this paper, we propose two distributed solutions, which protect users’ privacy and achieve optimal social welfare. The first solution is designed based on the Lagrangian dual decomposition. A poplar iterative gradient algorithm is used to converge to the optimal value. Moreover, this distributed method is interpreted by our pricing framework. In the second solution, we first equivalently convert the original problem to an optimal pricing problem. Then, a distributed solution under the pricing framework via an efficient price-updating algorithm is proposed. Experimental results show that both two distributed solutions can achieve the maximum social welfare of a participatory smartphone system.     

Maximizing influence under influence loss constraint in social networks

Influence maximization is a fundamental research problem in social networks. Viral marketing, one of its applications, aims to select a small set of users to adopt a product, so that the word-of-mouth effect can subsequently trigger a large cascade of further adoption in social networks. The problem of influence maximization is to select a set of K nodes from a social network so that the spread of influence is maximized over the network. Previous research on mining top-K influential nodes assumes that all of the selected K nodes can propagate the influence as expected. However, some of the selected nodes may not function well in practice, which leads to influence loss of top-K nodes. In this paper, we study an alternative influence maximization problem which is naturally motivated by the reliability constraint of nodes in social networks. We aim to find top-K influential nodes given a threshold of influence loss due to the failure of a subset of R(<K) nodes. To solve the new type of influence maximization problem, we propose an approach based on constrained simulated annealing and further improve its performance through efficiently estimating the influence loss. We provide experimental results over multiple real-world social networks in support. This research will further support practical applications of social networks in various domains particularly where reliability would be a main concern in a system deployment.     

Co-occurrence prediction in a large location-based social network

Location-based social network (LBSN) is at the forefront of emerging trends in social network services (SNS) since the users in LBSN are allowed to “check-in” the places (locations) when they visit them. The accurate geographical and temporal information of these check-in actions are provided by the end-user GPS-enabled mobile devices, and recorded by the LBSN system. In this paper, we analyze and mine a big LBSN data, Gowalla, collected by us. First, we investigate the relationship between the spatio-temporal co-occurrences and social ties, and the results show that the co-occurrences are strongly correlative with the social ties. Second, we present a study of predicting two users whether or not they will meet (co-occur) at a place in a given future time, by exploring their check-in habits. In particular, we first introduce two new concepts, bag-of-location and bag-of-time-lag, to characterize user’s check-in habits. Based on such bag representations, we define a similarity metric called habits similarity to measure the similarity between two users’ check-in habits. Then we propose a machine learning formula for predicting co-occurrence based on the social ties and habits similarities. Finally, we conduct extensive experiments on our dataset, and the results demonstrate the effectiveness of the proposed method.     

Simple models of network access,with applications to the design of joint rate and admission control

At the access to networks, in contrast to the core, distances and feedback delays, as well as link capacities are small, which has network engineering implications that are investigated in this paper. We consider a single point in the access network which multiplexes several bursty users. The users adapt their sending rates based on feedback from the access multiplexer. Important parameters are the user’s peak transmission rate p, which is the access line speed, the user’s guaranteed minimum rate r, and the bound ϵ on the fraction of lost data.Two feedback schemes are proposed. In both schemes the users are allowed to send at rate p if the system is relatively lightly loaded, at rate r during periods of congestion, and at a rate between r and p, in an intermediate region. For both feedback schemes we present an exact analysis, under the assumption that the users’ job sizes and think times have exponential distributions. We use our techniques to design the schemes jointly with admission control, i.e., the selection of the number of admissible users, to maximize throughput for given p, r, and ϵ. Next we consider the case in which the number of users is large. Under a specific scaling, we derive explicit large deviations asymptotics for both models. We discuss the extension to general distributions of user data and think times.     

Web news mining in an evolving framework

Online news has become one of the major channels for Internet users to get news. News websites are daily overwhelmed with plenty of news articles. Huge amounts of online news articles are generated and updated everyday, and the processing and analysis of this large corpus of data is an important challenge. This challenge needs to be tackled by using big data techniques which process large volume of data within limited run times. Also, since we are heading into a social-media data explosion, techniques such as text mining or social network analysis need to be seriously taken into consideration.In this work we focus on one of the most common daily activities: web news reading. News websites produce thousands of articles covering a wide spectrum of topics or categories which can be considered as a big data problem. In order to extract useful information, these news articles need to be processed by using big data techniques. In this context, we present an approach for classifying huge amounts of different news articles into various categories (topic areas) based on the text content of the articles. Since these categories are constantly updated with new articles, our approach is based on Evolving Fuzzy Systems (EFS). The EFS can update in real time the model that describes a category according to the changes in the content of the corresponding articles. The novelty of the proposed system relies in the treatment of the web news articles to be used by these systems and the implementation and adjustment of them for this task. Our proposal not only classifies news articles, but it also creates human interpretable models of the different categories. This approach has been successfully tested using real on-line news.     

Disambiguating identity web references using Web 2.0 data and semantics

As web users disseminate more of their personal information on the web, the possibility of these users becoming victims of lateral surveillance and identity theft increases. Therefore web resources containing this personal information, which we refer to as identity web references must be found and disambiguated to produce a unary set of web resources which refer to a given person. Such is the scale of the web that forcing web users to monitor their identity web references is not feasible, therefore automated approaches are required. However, automated approaches require background knowledge about the person whose identity web references are to be disambiguated. Within this paper we present a detailed approach to monitor the web presence of a given individual by obtaining background knowledge from Web 2.0 platforms to support automated disambiguation processes. We present a methodology for generating this background knowledge by exporting data from multiple Web 2.0 platforms as RDF data models and combining these models together for use as seed data. We present two disambiguation techniques; the first using a semi-supervised machine learning technique known as Self-training and the second using a graph-based technique known as Random Walks, we explain how the semantics of data supports the intrinsic functionalities of these techniques. We compare the performance of our presented disambiguation techniques against several baseline measures including human processing of the same data. We achieve an average precision level of 0.935 for Self-training and an average f-measure level of 0.705 for Random Walks in both cases outperforming several baselines measures.