ACM CIKM 2014 Workshops
23nd International Conference on Information and Knowledge Management (CIKM)
Shanghai, China. Nov 3-7, 2014
We are happy to announce that the following workshops will be held at CIKM 2014:
November 3, 2014
- DUBMOD2014 ---- Data-driven User Behavioral Modelling and Mining from Social Media (Afternoon, Half Day Workshop)
- ImBig 2014 ---- Interactive Mining of Big Data (Whole Day Workshop)
- LocWeb2014 ---- Location and the Web (Whole Day Workshop)
- PIKM2014 ---- Ph.D. Workshop in Information and Knowledge Management (Whole Day Workshop)
- Web-KR 2014 ---- Web-scale Knowledge Representation, Retrieval and Reasoning (Whole Day Workshop)
November 7, 2014
- DTMBIO 2014 ---- Data and Text Mining in Biomedical Informatics (Whole Day Workshop),
- DOLAP 2014 ---- Data Warehousing and OLAP (Whole Day Workshop)
- ESAIR’14 ---- Exploiting Semantic Annotations in Information Retrieval (Whole Day Workshop)
- PSBD 2014 ----Privacy and Security of Big Data (Afternoon, Whole Day Workshop)
Cancelled: LL'14 ---- Living Labs for Information Retrieval Evaluation Workshop
DTMBIO 14 organizers are pleased to announce that the eighth DTMBIO will be held in conjunction with CIKM, one of the largest data and text mining conferences. While CIKM presents the state-of-the-art research in informatics with the primary focus on data and text mining, the main focus of DTMBIO is on biomedical and healthcare informatics. DTMBIO delegates will bring forth interesting applications of up-to-date informatics in the context of biomedical research.
Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. These data can be used to better understand people (e.g., personality traits, perceptions, and preferences) and predict their behavior (e.g., their future location or likelihood of responding to an inquiry). As a result, a deeper understanding of users and their behavior can benefit a wide range of intelligent applications, such as advertising, social recommender systems, and personalized knowledge management. These applications will also benefit individual users themselves and optimize their experience across a wide variety of domains, such as retail, healthcare, and education. Since mining and understanding user behavior from social media often requires interdisciplinary effort, including machine learning, text mining, human-computer interaction, and social science, our workshop aims to bring together researchers and practitioners from multiple fields to discuss the creation of deeper models of individual users by mining the content that they publish and the social networking behavior that they exhibit. On the other hand, mining user behavior from public social media data may also reveal information that users would prefer to keep private. In this workshop we will also discuss possible mechanisms that users might employ to monitor what information has been revealed about themselves on social media and obfuscate any sensitive information.
There is an increasing amount of structure on the Web as a result of modern Web languages, user tagging and annotation, emerging robust NLP tools, and an ever growing volume of linked data. These meaningful, semantic, annotations hold the promise to significantly enhance information access, by enhancing the depth of analysis of today's systems. Currently, we have only started exploring the possibilities and only begin to understand how these valuable semantic cues can be put to fruitful use. To complicate matters, standard text search excels at shallow information needs expressed by short keyword queries, and here semantic annotation contributes very little, if anything. The goal of the ESAIR'14 is to advance the general research agenda on this core problem, with an explicit focus on two of the most challenging aspects to address in the coming years. First, there is a need to explore more articulate queries, with concepts and relations linking their statement of request to existing semantic models as offered by emerging knowledge bases (DBpedia, Freebase). Second, there is a need to extend the query suggestion paradigm to dynamically negotiate longer queries exploring powerful new aspects or facets of the underlying information need.
We are in the era of big data. Massive datasets surpassing terabytes and petabytes from all different real world applications, from social network analysis to bioinformatics, are now commonplace. They arise in numerous settings in science, government, and enterprises. Because of the rapid development of the hardware technology such as storage and communication systems, there are more and more digitized data that are readily available. Effective utilization and making sense of those data has been one research topic that has attracted huge amounts of interests from different fields, where Data Mining, as a field of mining knowledge and insights from massive data, plays an important role. One important aspect for exploring big data is interdisciplinarity, i.e., the data scientists need to work with domain experts owning those data to understand their needs and explain them the mined data-driven insights, get their inputs and feedbacks, and update the model to make it more accurate. This process will be iterated over time. Because a lot of interactions are involved between domain experts and computational models in this whole process, we usually call it interactive mining.
There are several important and challenging aspects of the interactive mining process:
- Efficient Analytical Algorithm. Deriving desired insights from big data and presenting them on the user interface in a timely fashion
- Intelligent User Interface. Providing the data driven insights on a smart interface such that the user can easily understand and provide their feedbacks
- Effective Data Management. Effectively managing (e.g., caching and sampling) the huge volume of data to support the interactive mining process
The focus of this workshop is to gather together the researchers from all relevant fields to share their experience and opinions on interactive mining of big data, with emphasis on interactivity and effective integration of techniques from data mining, visualization and human-computer interaction. In other words, we intend to explore how the best of these different but related domains can be combined such that the sum is greater than the parts. We will solicit a list of program committee members who are very active in this area, and guarantee each submission gets peer reviewed by at least three of them. We will also invite three to four high-profile researchers as keynote speakers and deliver invited talks.
In the past few years the information retrieval (IR) community has been exploring ways to move further away from the Cranfield-style evaluation paradigm, and make evaluations more "realistic". The basic idea of living labs for IR is to provide a central and shared experimental environment to perform experiments in situ, with real users doing real tasks using real-world applications. Living labs offer a new and exciting opportunity to the IR community to undertake meaningful and applicable research. This year’s living labs workshop aims to bring people together, for the second time, interested in progressing the living labs for IR evaluation methodology. An interactive forum for researchers to share ideas and initiate collaborations will be provided. The workshop also features a live challenge, focusing on two use-cases: product search (on an e-commerce site) and local domain search (on a university’s website). For each of these tasks, challenge participants will have access to product/webpage information, usage and query log data through an API and will be able to test their approaches in a live setting. See living-labs.net/challenge/ for details.
Location has quickly moved from the next hot thing into being accepted as an important aspect of the Web and, especially, the mobile Web. Its importance is growing even more, as mobile access is surpassing other forms of Web usage and many players adopt a mobile-first strategy. Location also plays a role in the form of the explicit or implicit location of resources, locations described in content, location of users, location APIs, or mobile apps, being also used in geospatial-aware data mining or large-scale analytics. It is thus a strong driver behind many recent innovations and research activities.LocWeb 2014 solicits submissions under the main theme of location-aware information access as a cross-cutting issue in Web research and technology, with subtopics related to search, retrieval, analytics, mining, extraction, mobility, apps, services, and systems.
URL: Location and the Web
PIKM 2014 calls for papers that should propose research ideas which can mature into a dissertation. The authors could be Ph.D. students or Masters students aspiring to get a Ph.D. and having in mind a clear idea of a proposal. Students could also submit work on one or more sub-problems of their dissertation. The papers should address the research issues in their proposal focusing on the challenges in solving them. They could also include the proposed techniques to solve the given problems. Preliminary experimental evaluation should be included. However, it should be clear that the work is ongoing. A wide range of topics on any area in databases, information retrieval and knowledge management can be presented at this workshop.
The 1st International Workshop on Privacy and Security of Big Data (PSBD 2014) focuses the attention on privacy and security research issues in the context of Big Data, a vibrant and challenging research context which is playing a leading role in the Database research community. Indeed, while Big Data is gaining the attention from the research community, also driven by some relevant technological innovations (like Clouds) as well as novel paradigms (like social networks), the issues of privacy and security of Big Data represent a fundamental problem in this research context, due to the fact Big Data are typically published online for supporting knowledge management and fruition processes and, in addition to this, such data are usually handled by multiple owners, with possible secure multi-part computation issues. Some of the hot topics in the context privacy and security of Big Data include: (i) privacy and security of Big Data integration and exchange; (ii) privacy and security of Big Data in data-intensive Cloud computing; (iii) system architectures in support of privacy and security of Big Data, e.g., GPUs: (iv) privacy and security issues of Big Data querying and analysis.
The World Wide Web has become the carrier for the largest human knowledge repository in history. As its knowledge bases are growing towards a practically infinite volume, Web-scale Knowledge Representation, Retrieval, and Reasoning (Web-KR) is becoming a real issue and an urgent task. Although the Web community has developed a number of knowledge representation languages and reasoning methods, when the volume goes Web-scale, existing approaches meet many challenging problems, regarding scalability, inconsistency, uncertainty and dynamics. Hence, a unified approach to Web-KR needs to be developed. This workshop aims at bringing together researchers from Web research, Artificial Intelligence (AI), high performance computing, cognitive science, knowledge management, and machine learning to discuss all issues of Web-KR in a synergistic setting.