Showing papers on "Personalization published in 2015"
Abstract: ‘The Logic of Connective Action’ by W. Lance Bennett and Alexandra Segerberg investigates patterns of participation and modes of action in contemporary protest politics that are characterized by increasingly individualized publics in which participants join protests more as individuals than as members of organizations. Bennett and Segerberg claim that in such a context, digital media do much more than simply support the organization of protest. Rather, they become to some extent actors in themselves, since they have a crucial role in shaping the organizational structures that underlie social movements and their mobilizations. Starting from these assumptions, Bennett and Segerberg explore three crucial themes that are outlined in the Introduction to the volume. The first one refers to the personalization and individualization of politics and their consequences at the level of political participation, especially at the grassroots level of social movements and advocacy coalitions. The second theme regards the intertwining of (digital) communication with processes and mechanisms of political participation from below, with the former increasingly embedded in the latter to the extent that communication becomes organization. The third theme concerns the different logics that characterize the organization of mobilizations and the related models of action, from the well-known collective action processes to the emerging forms of connective action, which can be enabled by established social movement organizations and coalitions or by the very actions of individual protesters that form the crowds taking part in mobilizations. This last theme is discussed, from a theoretical viewpoint, in Chapter 1 that contrasts the logic of connective action with the logic of collective action. In particular, the latter rests on two main features that are absent in the logic of collective action: personal action frames, meaning frames that are easily personalized by individual protesters who join the mobilization, and the presence of personal communication technologies that allow the quick and easy sharing of media contents across multiple media platforms. The logic of connective action, however, can be found in at least two different configurations. On the one side of the spectrum, we find organizationally enabled connective actions, in which social movement organizations decide to release some of their control of the mobilization process to allow individualized publics the appropriation of the protest campaign in point. On the other side of the spectrum, we find crowd-enabled connective action in which social movement organizations seem to be absent. Instead, mobilization takes 594581 MCS0010.1177/0163443715594581Media, Culture & SocietyBook Reviews research-article2015
715 citations
TL;DR: In this article, the authors investigate the personalization paradox in online personalized advertising and find that consumers exhibit greater click-through intentions in response to more personalized advertisements, in contrast with their reactions when firms collect information covertly, reflecting the feelings of vulnerability that consumers experience when firms undertake covert information collection.
614 citations
TL;DR: This study identifies the requirements of smart technologies for experience creation, including information aggregation, ubiquitous mobile connectedness and real time synchronization and highlights how smart technology integration can lead to two distinct levels of personalized tourism experiences.
Abstract: Recent advances in the field of technology have led to the emergence of innovative technological smart solutions providing unprecedented opportunities for application in the tourism and hospitality industry. With intensified competition in the tourism market place, it has become paramount for businesses to explore the potential of technologies, not only to optimize existing processes but facilitate the creation of more meaningful and personalized services and experiences. This study aims to bridge the current knowledge gap between smart technologies and experience personalization to understand how smart mobile technologies can facilitate personalized experiences in the context of the hospitality industry. By adopting a qualitative case study approach, this paper makes a two-fold contribution; it a) identifies the requirements of smart technologies for experience creation, including information aggregation, ubiquitous mobile connectedness and real time synchronization and b) highlights how smart technology integration can lead to two distinct levels of personalized tourism experiences. The paper concludes with the development of a model depicting the dynamic process of experience personalization and a discussion of the strategic implications for tourism and hospitality management and research.
535 citations
TL;DR: In this paper, the authors investigate how trust moderates the impact of ad personalization on consumers' internal and external responses in the lab and propose a two-dimensional conceptualization of ad personalizedization: First, a banner's personalization depth defines how closely the ad reflects a consumer's interests.
387 citations
TL;DR: It is shown that, although personalization can substantially enhance banner effectiveness, its impact hinges on its interplay with timing and placement factors, and click-through increases at an early information state of the purchase decision process and ad effectiveness on motive congruent or incongruent display websites.
Abstract: Firms track consumers' shopping behaviors in their online stores to provide individually personalized banners through a method called retargeting. We use data from two large-scale field experiments and two lab experiments to show that, although personalization can substantially enhance banner effectiveness, its impact hinges on its interplay with timing and placement factors. First, personalization increases click-through especially at an early information state of the purchase decision process. Here, banners with a high degree of content personalization DCP are most effective when a consumer has just visited the advertiser's online store, but quickly lose effectiveness as time passes since that last visit. We call this phenomenon overpersonalization. Medium DCP banners, on the other hand, are initially less effective, but more persistent, so that they outperform high DCP banners over time. Second, personalization increases click-through irrespective of whether banners appear on motive congruent or incongruent display websites. In terms of view-through, however, personalization increases ad effectiveness only on motive congruent websites, but decreases it on incongruent websites. We demonstrate in the lab how perceptions of ad informativeness and intrusiveness drive these results depending on consumers' experiential or goal-directed Web browsing modes.
334 citations
01 May 2015-International Journal of Human-computer Studies \/ International Journal of Man-machine Studies
TL;DR: How persuasive technologies can be made adaptive to users is discussed, and persuasion profiling as a method to personalize the persuasive messages used by a system to influence its users is presented.
Abstract: This paper discusses how persuasive technologies can be made adaptive to users. We present persuasion profiling as a method to personalize the persuasive messages used by a system to influence its users. This type of personalization can be based on explicit measures of users? tendencies to comply to distinct persuasive strategies: measures based on standardized questionnaire scores of users. However, persuasion profiling can also be implemented using implicit, behavioral measures of user traits. We present three case studies involving the design, implementation, and field deployment of personalized persuasive technologies, and we detail four design requirements. In each case study we show how these design requirements are implemented. In the discussion we highlight avenues for future research in the field of adaptive persuasive technologies. Author-HighlightsPersuasive technologies can be more effective if they are personalized.We introduce persuasion profiles to personalize persuasive messages.Persuasion profiles can be effective using implicit or explicit measures.In three case studies we show the effects of personalized persuasion.
303 citations
14 Dec 2015
TL;DR: In this meta-review 82 recommender systems from 35 different countries have been investigated and categorised according to a given classification framework and analysed for their contribution to the evolution of the RecSysTEL research field.
Abstract: This chapter presents an analysis of recommender systems in Technology-Enhanced Learning along their 15 years existence (2000–2014). All recommender systems considered for the review aim to support educational stakeholders by personalising the learning process. In this meta-review 82 recommender systems from 35 different countries have been investigated and categorised according to a given classification framework. The reviewed systems have been classified into seven clusters according to their characteristics and analysed for their contribution to the evolution of the RecSysTEL research field. Current challenges have been identified to lead the work of the forthcoming years.
255 citations
TL;DR: In this article, the authors make an updated review of the eLearning concept and its definitions that have been provided from the experience and perspective of our research group GRIAL (Research Group in Interaction and eLearning), coinciding with the tenth anniversary of the current status of e-learning systems.
Abstract: The continuous advances in technology cause innovation-acceptation-consolidationobsolescence flows regarding the knowledge and technology management strategies, both ad hoc and planned, of the corporations and also, in a different scale, of the individuals. Teaching and learning processes are not obviously unaware of this situation. The irruption of Information and Communication Technologies as educational tools mean both a conceptual and a methodological turning point in the way that institutions, educational or not, face training processes and learning management, especially with regard to the concept of distance education, which evolves, in a more or less significant way, when it adopts Internet as media; that is how the eLearning concept rises. However, from the first eLearning experiences, too much settled on the concept of platform or Learning Management System, up to the present times, there have been significant changes, again in both technological and methodological levels. It is important to underline, among others, the influence of social media in the daily habits of users. This way, an increased demand of learning personalization it is shown, as so as a complete connectivity with other peers, an unlimited access to resources and information sources, a complete flexibility in the way, place and time they access, and a natural and necessary coexistence of both formal and informal learning flows. Thus, the “traditional” eLearning platforms, despite their large penetration and consolidation, need to evolve and open themselves to support this rich fan of possibilities demanded by the users, ceasing to be the centre technological attention to become another component into a complex digital ecosystem oriented to the learning and knowledge management, both at institutional and personal levels. It is therefore necessary to make an updated review of the eLearning concept and its definitions that have been provided from the experience and perspective of our research group GRIAL (Research Group in InterAction and eLearning), coinciding with the tenth anniversary of the “Current status of e-learning systems” paper.
232 citations
TL;DR: This study reviews and synthesizes extant empirical IS studies of RS to provide a coherent view of research on RS and identify gaps and future directions, and surface research gaps.
Abstract: An online recommendation system (RS) involves using information technology and customer information to tailor electronic commerce interactions between a business and individual customers. Extant information systems (IS) studies on RS have approached the phenomenon from many different perspectives, and our understanding of the nature and impacts of RS is fragmented. The current study reviews and synthesizes extant empirical IS studies to provide a coherent view of research on RS and identify gaps and future directions. Specifically, we review 40 empirical studies of RS published in 31 IS journals and five IS conference proceedings between 1990 and 2013. Using a recommendation process theoretical framework, we categorize these studies in three major areas addressed by RS research: understanding consumers, delivering recommendations, and the impacts of RS. We review and synthesize the extant literature in each area and across areas. Based on the review and synthesis, we surface research gaps and provide suggestions and potential directions for future research on recommendation systems.
221 citations
Proceedings Article•
18 May 2015TL;DR: The technical program of the 24th International World Wide Web Conference (WWW 2015) as mentioned in this paper has received a record number of 929 submissions for the research program, distributed over the following 11 Web-related technical areas: Behavior Analysis and Personalization, Crowdsourcing Systems and Social Media, Content Analysis, Internet Economics and Monetization, Pervasive Web and Mobility, Security and Privacy, Semantic Web, Web Infrastructure -- Data Centers, Content Delivery Networks, Web Mining, and Web Search Systems and Applications.
Abstract: We are delighted to present the technical program of the 24th International World Wide Web Conference (WWW 2015), held from May 18 to 22, 2015 in Florence, Italy. Since its inception in 1994, the International World Wide Web Conference has been the premier venue for researchers, academics, businesses, and standards organizations to convene and discuss the latest Web research and technologies.
This year, we have received a record number of 929 submissions for the research program, distributed over the following 11 Web-related technical areas: (1) Behavior Analysis and Personalization, (2) Crowdsourcing Systems and Social Media, (3) Content Analysis, (4) Internet Economics and Monetization, (5) Pervasive Web and Mobility, (6) Security and Privacy, (7) Semantic Web, (8) Social Networks and Graph Analysis, Web Infrastructure -- Data Centers, (9) Content Delivery Networks, (10) Web Mining, and (11) Web Search Systems and Applications. All submissions underwent a rigorous reviewing process, where at least three expert Program Committee (PC) members reviewed each submission and a fourth expert lead the discussion of the reviews. In total, a highly skilled and diverse team of 554 PC members were involved in the reviewing process and they collectively produced over 3000 reviews. The PC members were recruited by area chairs, who also oversaw the reviewing of the submissions in their area, made initial recommendations to accept or reject the submissions in their area, and participated in a two-day area chair meeting held in Kaiserslautern, Germany. The final acceptance decisions were made at the meeting, where the recommendations of the area chairs were discussed and voted on by all area chairs and the PC chairs. Submissions, where area chairs were conflicted, were handled separately PC chairs. The outcome of the meeting was to accept a total of 131 (14.1%) papers for the research program. We believe that these 131 accepted papers represent some of the best Web-related research conducted over the last year and we are confident that they would lead to fruitful discussions and new ideas at the conference.
218 citations
TL;DR: The aim of this paper is to present the various limitations of the current generation of recommendation techniques and possible extensions with model for tagging activities and tag-based recommender systems, which can apply to e-learning environments in order to provide better recommendation capabilities.
Abstract: With the development of sophisticated e-learning environments, personalization is becoming an important feature in e-learning systems due to the differences in background, goals, capabilities and personalities of the large numbers of learners. Personalization can achieve using different type of recommendation techniques. This paper presents an overview of the most important requirements and challenges for designing a recommender system in e-learning environments. The aim of this paper is to present the various limitations of the current generation of recommendation techniques and possible extensions with model for tagging activities and tag-based recommender systems, which can apply to e-learning environments in order to provide better recommendation capabilities.
TL;DR: In this paper, the impact of perceived personalization on consumer responses to advertising on Facebook, a popular social network site (SNS), was studied and the results showed that perceived personalisation improves responses toward Facebook ads, through perceived relevance.
Abstract: We study the impact of perceived personalization on consumer responses to advertising on Facebook, a popular social network site (SNS). Based on two experiments, we test a moderated mediation model with perceived relevance as the mediator and respondents' attitudes toward Facebook as the moderator of the relationship between perceived personalization on one hand and brand attitude and click intention on the other. The results show that perceived personalization improves responses toward Facebook ads, through perceived relevance. The moderating impact of attitude toward Facebook is significant only in the second study. There, the positive effect of perceived personalization of Facebook advertisements on click intention is stronger for participants with more positive attitudes toward Facebook.
TL;DR: It is concluded that the power that design can have has not been used to its full potential in Web-based interventions and is proposed looking at design research as a source of inspiration for new design approaches.
Abstract: Nowadays, technology is increasingly used to increase people’s well-being. For example, many mobile and Web-based apps have been developed that can support people to become mentally fit or to manage their daily diet. However, analyses of current Web-based interventions show that many systems are only used by a specific group of users (eg, women, highly educated), and that even they often do not persist and drop out as the intervention unfolds. In this paper, we assess the impact of design features of Web-based interventions on reach and adherence and conclude that the power that design can have has not been used to its full potential. We propose looking at design research as a source of inspiration for new (to the field) design approaches. The paper goes on to specify and discuss three of these approaches: personalization, ambient information, and use of metaphors. Central to our viewpoint is the role of positive affect triggered by well-designed persuasive features to boost adherence and well-being. Finally, we discuss the future of persuasive eHealth interventions and suggest avenues for follow-up research.
18 May 2015
TL;DR: This work implemented and built a topic recommender predicting user's topical interests using their actions within Google+, and experimentally showed that it obtained better and cleaner signals than baseline methods, and is able to more accurately predict topic interests as well as achieve better coverage.
Abstract: Many recommenders aim to provide relevant recommendations to users by building personal topic interest profiles and then using these profiles to find interesting contents for the user. In social media, recommender systems build user profiles by directly combining users' topic interest signals from a wide variety of consumption and publishing behaviors, such as social media posts they authored, commented on, +1'd or liked. Here we propose to separately model users' topical interests that come from these various behavioral signals in order to construct better user profiles. Intuitively, since publishing a post requires more effort, the topic interests coming from publishing signals should be more accurate of a user's central interest than, say, a simple gesture such as a +1. By separating a single user's interest profile into several behavioral profiles, we obtain better and cleaner topic interest signals, as well as enabling topic prediction for different types of behavior, such as topics that the user might +1 or comment on, but might never write a post on that topic. To do this at large scales in Google+, we employed matrix factorization techniques to model each user's behaviors as a separate example entry in the input user-by-topic matrix. Using this technique, which we call "behavioral factorization", we implemented and built a topic recommender predicting user's topical interests using their actions within Google+. We experimentally showed that we obtained better and cleaner signals than baseline methods, and are able to more accurately predict topic interests as well as achieve better coverage.
TL;DR: The results demonstrate that the material features of mobile technologies offer five specific affordances that mobile workers use in managing work-life boundaries: mobility, connectedness, interoperability, identifiability and personalization.
Abstract: Purpose – The purpose of this paper is to explore the role that mobile technologies play in mobile workers’ efforts to manage the boundaries between work and non-work domains. Previous theories of work-life boundary management frame boundary management strategies as a range between the segmentation and integration of work-life domains, but fail to provide a satisfactory account of technology’s role. Design/methodology/approach – The authors apply the concept of affordances, defined as the relationship between users’ abilities and features of mobile technology, in two field studies of a total of 25 mobile workers who used a variety of mobile devices and services. Findings – The results demonstrate that the material features of mobile technologies offer five specific affordances that mobile workers use in managing work-life boundaries: mobility, connectedness, interoperability, identifiability and personalization. These affordances persist in their influence across time, despite their connection to differen...
1 Apr 2015
TL;DR: The effectiveness of utilizing semantic knowledge of items to enhance the recommendation quality is presented and a new Inferential Ontology-based Semantic Similarity (IOBSS) measure is proposed to evaluate semantic similarity between items in a specific domain of interest.
Abstract: Recommender systems are effectively used as a personalized information filtering technology to automatically predict and identify a set of interesting items on behalf of users according to their personal needs and preferences. Collaborative Filtering (CF) approach is commonly used in the context of recommender systems; however, obtaining better prediction accuracy and overcoming the main limitations of the standard CF recommendation algorithms, such as sparsity and cold-start item problems, remain a significant challenge. Recent developments in personalization and recommendation techniques support the use of semantic enhanced hybrid recommender systems, which incorporate ontology-based semantic similarity measure with other recommendation approaches to improve the quality of recommendations. Consequently, this paper presents the effectiveness of utilizing semantic knowledge of items to enhance the recommendation quality. It proposes a new Inferential Ontology-based Semantic Similarity (IOBSS) measure to evaluate semantic similarity between items in a specific domain of interest by taking into account their explicit hierarchical relationships, shared attributes and implicit relationships. The paper further proposes a hybrid semantic enhanced recommendation approach by combining the new IOBSS measure and the standard item-based CF approach. A set of experiments with promising results validates the effectiveness of the proposed hybrid approach, using a case study of the Australian e-Government tourism services. A hybrid semantic enhanced recommendation approachA new Inferential Ontology-based Semantic Similarity (IOBSS) between two ontological instancesA few new concepts: Association, Associate Network and Common Associate Pair SetA case study of Australian e-Government tourism services
TL;DR: A research model is developed that proposes users’ preference fit and perceived enjoyment as two key intervening mechanisms that carry over the differential effects of content and design personalization cues on users�’ willingness to stick to a website and to pay for website offerings and finds that a combination ofcontent and designpersonalization cues is ineffective—or even counterproductive—in increasing preferenceFit and users” WTP above and beyond the levels generated by content cues alone.
Abstract: Although various kinds of personalization cues are pervasively used on websites, previous research studies have treated web personalization primarily as a coarse-grained, monolithic block (e.g., by comparing personalization vs. nonpersonalization or personalization vs. privacy) rather than as a combination of salient types of personalization cues that may create—either jointly or separately—different effects on user assessments of website value. Based on the stimulus–organism–response framework, we develop a research model that proposes users’ preference fit and perceived enjoyment as two key intervening mechanisms that carry over the differential effects of content and design personalization cues on users’ willingness to stick to a website and to pay for website offerings. In a field experiment with 206 subjects using a real-life news aggregator website, our findings provide evidence in support of different effect paths emanating from content and design personalization cues. Furthermore, we show ...
28 Oct 2015
TL;DR: This paper proposes a novel methodology to explore the impact of location-based personalization on Google Search results, and observes that differences in search results due to personalization grow as physical distance increases.
Abstract: To cope with the immense amount of content on the web, search engines often use complex algorithms to personalize search results for individual users. However, personalization of search results has led to worries about the Filter Bubble Effect, where the personalization algorithm decides that some useful information is irrelevant to the user, and thus prevents them from locating it. In this paper, we propose a novel methodology to explore the impact of location-based personalization on Google Search results. Assessing the relationship between location and personalization is crucial, since users' geolocation can be used as a proxy for other demographic traits, like race, income, educational attainment, and political affiliation. In other words, does location-based personalization trap users in geolocal Filter Bubbles?Using our methodology, we collected 30 days of search results from Google Search in response to 240 different queries. By comparing search results gathered from 59 GPS coordinates around the US at three different granularities (county, state, and national), we are able to observe that differences in search results due to personalization grow as physical distance increases. However these differences are highly dependent on what a user searches for: queries for local establishments receive 4-5 different results per page, while more general terms exhibit essentially no personalization.
18 Apr 2015
TL;DR: It is shown for the first time at this scale that a combined spatial-language model reduces word error rate from a pre-model baseline of 38.4% down to 5.7%, and that LM personalization can improve this further to 4.6%.
Abstract: Modern smartphones correct typing errors and learn user-specific words (such as proper names). Both techniques are useful, yet little has been published about their technical specifics and concrete benefits. One reason is that typing accuracy is difficult to measure empirically on a large scale. We describe a closed-loop, smart touch keyboard (STK) evaluation system that we have implemented to solve this problem. It includes a principled typing simulator for generating human-like noisy touch input, a simple-yet-effective decoder for reconstructing typed words from such spatial data, a large web-scale background language model (LM), and a method for incorporating LM personalization. Using the Enron email corpus as a personalization test set, we show for the first time at this scale that a combined spatial-language model reduces word error rate from a pre-model baseline of 38.4% down to 5.7%, and that LM personalization can improve this further to 4.6%.
Posted Content•
TL;DR: In this paper, the authors investigate the effect of personalization and scarcity on consumer referral behavior in an online fashion service named StyleCrowd and find that personalization cues are particularly effective when scarcity is absent, while scarcity is prevalent.
Abstract: Against the backdrop of consumers being deluged with traditional online advertising, which is increasingly manifesting in inefficient conversion outcomes, viral marketing has become a pivotal component of marketing strategy. However, despite a robust understanding about the impact of viral marketing as well as of factors that drive consumer referral engagement, we know very little about the effect of traditional promotional tactics on consumer referral decisions. Drawing on a randomized field experiment in the context of an online fashion service named StyleCrowd, we investigate the effects of scarcity and personalization, two classical promotional cues that have become ubiquitous on the web and have received only minimal attention hitherto, on actual referral behavior. Our analysis reveals that using these cues in promotional campaigns is a balancing act: While scarcity cues affect referral propensity regardless of whether a campaign is personalized or not, personalization cues are particularly effective when scarcity is absent, yet are cancelled out when scarcity is prevalent. We demonstrate that consumers' perceptions of offer value drive the impact of scarcity on referral likelihood, while consumer gratitude vis-a-vis the marketer is the underlying mechanism for personalization's influence on referral decisions.
TL;DR: In this article, the authors developed and empirically validated a conceptual model based on an extended version of the privacy calculus model that explained consumers' willingness to disclose personal information via hotel: apps and found that trust in the app and the overall value of information disclosure has significant impacts on personal information disclosure via apps.
TL;DR: This article designs a centralized controller to manage physical devices and provide an interface for data collection, transmission, and processing to develop a more flexible health surveillance application that is full of personalization.
Abstract: With the increasingly serious problem of the aging population, creating an efficient and real-time health management and feedback system based on the healthcare Internet of Things (HealthIoT) is an urgent need. Specifically, wearable technology and robotics can enable a user to collect the required human signals in a comfortable way. HealthIoT is the basic infrastructure for realizing health surveillance, and should be flexible to support multiple application demands and facilitate the management of infrastructure. Therefore, enlightened by the software defined network, we put forward a smart healthcare oriented control method to software define health monitoring in order to make the network more elastic. In this article, we design a centralized controller to manage physical devices and provide an interface for data collection, transmission, and processing to develop a more flexible health surveillance application that is full of personalization. With these distinguished characteristics, various applications can coexist in the shared infrastructure, and each application can demand that the controller customize its own data collection, transmission, and processing as required, and pass the specific configuration of the physical device. This article discusses the background, advantages, and design details of the architecture proposed, which is achieved by an open-ended question and a potential solution. It opens a new research direction of HealthIoT and smart homes.
TL;DR: Results from a between-subjects experiment showed that customization and locational congruity were effective strategies for inducing positive attitudes about LBA and its service quality and the ad's perceived intrusiveness was found to mediate the effects of product involvement on participants' attitudes toward LBA.
01 Jun 2015-International Journal of Human-computer Studies \/ International Journal of Man-machine Studies
TL;DR: This research investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion, and introduced an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering.
Abstract: In this research we investigated the role of user controllability on personalized systems by implementing and studying a novel interactive recommender interface, SetFusion. We examined whether allowing the user to control the process of fusing or integrating different algorithms (i.e., different sources of relevance) resulted in increased engagement and a better user experience. The essential contribution of this research stems from the results of a user study (N=40) of controllability in a scenario where users could fuse different recommendation approaches, with the possibility of inspecting and filtering the items recommended. First, we introduce an interactive Venn diagram visualization, which combined with sliders, can provide an efficient visual paradigm for information filtering. Second, we provide a three-fold evaluation of the user experience: objective metrics, subjective user perception, and behavioral measures. Through the analysis of these metrics, we confirmed results from recent studies, such as the effect of trusting propensity on accepting the recommendations and also unveiled the importance of features such as being a native speaker. Our results present several implications for the design and implementation of user-controllable personalized systems. We explored user-controllable interfaces as extension of traditional-ranked lists.We introduced SetFusion, a controllable interface with sliders and a Venn diagram.We conducted a controlled user study on online conference article recommendation.Our evaluation had three dimensions: users' perception, behavioral and IR metrics.Controllable interface had a positive effect influenced by users' characteristics.
9 Aug 2015
TL;DR: This work proposes a parameter-free bandit strategy, which employs a principled resampling approach called online bootstrap, to derive the distribution of estimated models in an online manner and demonstrates the effectiveness of the proposed algorithm in terms of the click-through rate.
Abstract: Personalized recommendation services have gained increasing popularity and attention in recent years as most useful information can be accessed online in real-time. Most online recommender systems try to address the information needs of users by virtue of both user and content information. Despite extensive recent advances, the problem of personalized recommendation remains challenging for at least two reasons. First, the user and item repositories undergo frequent changes, which makes traditional recommendation algorithms ineffective. Second, the so-called cold-start problem is difficult to address, as the information for learning a recommendation model is limited for new items or new users. Both challenges are formed by the dilemma of exploration and exploitation. In this paper, we formulate personalized recommendation as a contextual bandit problem to solve the exploration/exploitation dilemma. Specifically in our work, we propose a parameter-free bandit strategy, which employs a principled resampling approach called online bootstrap, to derive the distribution of estimated models in an online manner. Under the paradigm of probability matching, the proposed algorithm randomly samples a model from the derived distribution for every recommendation. Extensive empirical experiments on two real-world collections of web data (including online advertising and news recommendation) demonstrate the effectiveness of the proposed algorithm in terms of the click-through rate. The experimental results also show that this proposed algorithm is robust in the cold-start situation, in which there is no sufficient data or knowledge to tune the hyper-parameters.
TL;DR: In this article, a draft of an article for the upcoming international encyclopedia of communication theory and philosophy is presented. But the article is not complete and the authors are still working on it.
Abstract: digitalization and digitization culture digitally pleased to share a draft of an article daniel kreiss and i are working on for the upcoming international encyclopedia of communication theory and philosophy we think this compliments some of the great work being done through the digital keywords project especially digital and analog we would appreciate any comments you care to give, critical questions for big data provocations for a the era of big data has begun computer scientists physicists economists mathematicians political scientists bio informaticists sociologists and other scholars are clamoring for access to the massive quantities of information produced by and about people things and their interactions, why david sometimes wins leadership organization and why david sometimes wins tells the story of cesar chavez and the united farm workers groundbreaking victory drawing important lessons from this dramatic tale since the 1900s large scale agricultural enterprises relied on migrant labor a cheap unorganized and powerless workforce
1 Jan 2015
TL;DR: This chapter uses Netflix personalization as a case study to describe several approaches and techniques used in a real-world recommendation system and pinpoint what it sees as some promising current research avenues and unsolved problems that deserve attention in this domain from an industry perspective.
Abstract: The Netflix Prize put a spotlight on the importance and use of recommender systems in real-world applications. Many the competition provided many lessons about how to approach recommendation and many more have been learned since the Grand Prize was awarded in 2009. The evolution of industrial applications of recommender systems has been driven by the availability of different kinds of user data and the level of interest for the area within the research community. The goal of this chapter is to give an up-to-date overview of recommender systems techniques used in an industrial setting. We will give a high-level description the practical use of recommendation and personalization techniques. We will highlight some of the main lessons learned from the Netflix Prize. We will then use Netflix personalization as a case study to describe several approaches and techniques used in a real-world recommendation system. Finally, we will pinpoint what we see as some promising current research avenues and unsolved problems that deserve attention in this domain from an industry perspective.
16 Sep 2015
TL;DR: This work builds and evaluates a system that incorporates user-tuned popularity and recency modifiers, allowing users to express concepts like "show more popular items" and finds that users who are given these controls evaluate the resulting recommendations much more positively.
Abstract: The essence of a recommender system is that it can recommend items personalized to the preferences of an individual user. But typically users are given no explicit control over this personalization, and are instead left guessing about how their actions affect the resulting recommendations. We hypothesize that any recommender algorithm will better fit some users' expectations than others, leaving opportunities for improvement. To address this challenge, we study a recommender that puts some control in the hands of users. Specifically, we build and evaluate a system that incorporates user-tuned popularity and recency modifiers, allowing users to express concepts like "show more popular items". We find that users who are given these controls evaluate the resulting recommendations much more positively. Further, we find that users diverge in their preferred settings, confirming the importance of giving control to users.
Journal Article•
TL;DR: It is found that simply providing a large number of information content features to online customers is not enough for companies looking to motivate customers to purchase, and information that is targeted to an individual customer influences customer satisfaction and purchase intention.
Abstract: A number of frameworks have been prescribed for online retailers, but still there exists little consensus regarding the amount of information and the level of customization needed to optimize customers' satisfaction and their purchase intention, and thereby increase sales performance Against this backdrop, this study aims to contribute to the current practical and theoretical discussions regarding the most effective ways to design and implement online retailers' website features by empirically examining the interplay between information content and website personalization, and their individual and interactive impact on performance By applying Structural Equation Modeling analysis to a sample of the top US retailers' websites, we find that simply providing a large number of information content features to online customers is not enough for companies looking to motivate customers to purchase However, information that is targeted to an individual customer influences customer satisfaction and purchase inte
TL;DR: Ideally, economic evaluations should take account of both interpretations of PM and consider physiology and preferences, and it is important for decision makers to be cognizant of the issues involved with the economic evaluation of PM.
Abstract: Context
This study assesses if, and how, existing methods for economic evaluation are applicable to the evaluation of personalized medicine (PM) and, if not, where extension to methods may be required.