Showing posts with label recommender systems. Show all posts
Showing posts with label recommender systems. Show all posts

Workshop NLP in the Enterprise: Envisioning the Next 10 Years

. Saturday, April 10, 2010
1 comments

The workshop "NLP in the Enterprise: Envisioining the next 10 years" (PLN-E) will be held in Valencia (Spain), as a satellite workshop of SEPLN 2010, on September 6-7, 2010.

PLN-E aims to become a meeting point among academic researchers and companies interested on technologies all along Natural Language Processing and other related technologies like text mining, information retrieval, opinion mining, etc.

Topics of Interest

We aim the submission of works that shows how NLP can help enterprises to solve problems, or develop new products and services. We expect 3 different types of works:

  • (Academic/enterprise) Research works at early stages but with a clear orientation to enterprise applications (products/services)
  • Works showing how a certain or several NLP technologies have been successfully used to solve a certain problem (such as developing a new product/service)
  • Works from companies explaining certain problems that can not be solved with the actual state of the art on NLP.

Topics of interest include, but are not limited to, the next topics:

A) New NLP Technologies with a clear Application in the Enterprise

    1. Opinion Mining and Sentiment Analysis
    2. Monolingual and Multilingual Information Systems
    3. Voice Question-Answering Systems
    4. Social Intelligent Systems
    5. Plagiarism Detection and Systems for Detecting Confidential Information
    6. Recommender Systems
    7. Illicit contents/Crimes Detection Systems

B) New Application Domains

    1. Social Media
    2. Mobile Devices
    3. Videoconsoles and TDT
    4. Virtual Worlds and Massive Multiplayer Games

C) Business Aspects of NLP

    1. New Business Models
    2. Unsolved Problems
    3. Scalability and Performance of NLP Technologies
    4. Production Environments for NLP Systems
    5. Real-World Datasets Descriptions
    6. Demands and Market Needs

Dates

  • Submission: 15 June, 2010
  • Notification of acceptance: 15 July, 2010
  • Camera Ready: 15 August, 2010
  • Workshop: 6/7 de September, 2010

CFPs on Recommender Systems

. Thursday, March 25, 2010
73 comments

There are several call for papers for conferences and journals related to Recommender Systems. Conferences:

Journals/Special Issues:
ACM RecSys workshops were published some days ago. There are 7 different workshops related to Recommender Systems, so we'll have more CFPs soon.

CFP: APRESW Extended to March 15

. Tuesday, March 09, 2010
2 comments

APRESW 2010 (1st International Workshop on Adaptation, Personalization and REcommendation in the Social-semantic Web), colocated under the ESWC 2010, has extended its deadline to March 15.

RecSys + ECML/PKDD = Barcelona, September

. Saturday, March 06, 2010
4 comments

This year's editions of RecSys (ACM Recommender Systems) and ECML/PKDD (European Conference on Machine Learning) will be held in Barcelona. ECML will be from 20th to 24th of September (Monday to Friday), and RecSys will start on Sunday (26th) and will finish 30th of September (thursday).

There is a clear topic relation between RecSys and ECML, in fact most of actual RecSys approaches has been proben in other fields (like data-mining, machine learning, information retrieval, etc.) before. For whom, like me, work around the two fields, is a great opportunity to assist two great conference in a single travel, and discover Barcelona, that is a really great city.

1st International Workshop on Adaptation, Personalization and REcommendation in the Social-semantic Web (APRESW 2010)

. Friday, January 08, 2010
23 comments

Call for Papers: 1st International Workshop on Adaptation, Personalization and REcommendation in the Social-semantic Web (APRESW 2010)
30 or 31 May 2010 | Heraklion, Greece
http://nets.ii.uam.es/apresw2010/

In conjunction with the
7th Extended Semantic Web Conference (ESWC 2010)
http://www.eswc2010.org/


+++++++++++++++
Important dates
+++++++++++++++

* Paper submission: 7 March 2010
* Notification of paper acceptance/rejection: 5 April 2010
* Camera-ready copies of accepted papers: 18 April, 2010
* APRESW 2010 Workshop: 30 or 31 May 2010

++++++++++
Motivation
++++++++++

During the last years, researchers and practitioners of the Semantic Web have progressively consolidated a number of very important achievements. Formal languages have been standardized to define ontology-based knowledge representations, logic formalisms and query models. Ontology engineering methodologies and tools have been proposed to ease the designing and populating of ontological knowledge bases. Reasoning engines have been implemented to exploit inference capabilities of ontologies, and semantic-based frameworks have been built to enrich the functionalities of Web services. These achievements are the pillars to deal with the complex challenge of bringing semantics to the Web.

The above gives a new ground to extend the focus of the Semantic Web by engaging it in other communities, where semantics can play an important role. The available semantic knowledge bases can be used to enrich and link additional repositories, ontology engineering techniques can be utilized to properly design and build ontologies in further real-world domains, and inference and query mechanisms can enhance classic information management and retrieval approaches.

Among these communities, this workshop aims to attract the attention of students and professionals both from academia and industry who take benefit of semantic-based techniques and technologies in within-application Adaptation, Personalization and Recommendation approaches. In parallel to the progress made in the Semantic Web research topics, there have been appearing works in the above areas that use ontologies to model the user’s preferences, tastes and interests, and exploit these personal features together with meta-information about multimedia contents in order to provide the user with adaptation and personalization capabilities for different purposes such as information retrieval and item recommendation.

Moreover, with the advent of the Web 2.0 (also called the Social Web), the potential study and development of those approaches have increased exponentially. Social networks allow people to provide explicit relationships with others, and find out implicit user similarities based on their profiles. Social tagging services offer the opportunity to easily create and exploit personal knowledge representations. Wiki-style sites represent an environment where the community contributes and shares information, and blogs are media in which users express subjective opinions.

In all of these scenarios, adaptation, personalization and recommendation are core functionalities. However, the understanding and exploitation of the semantics underlying user and item profiles are still open issues.

++++++++++++++++++
Topics of interest
++++++++++++++++++

The workshop will focus on establishing user/usage models for adaptation, personalization and recommendation approaches for the Social-semantic Web.

Topics of interest include, but are not limited to the exploitation of the Web of Data, the identification of semantics underlying social annotations of multimedia contents, and the application of semantic-based techniques and technologies in research fields related to:

* Personalized access to multimedia content
* Content-based recommendation and collaborative filtering
* Adaptive exploration of multimedia content
* Adaptive user interfaces for multimedia content browsing and searching
* Community extraction and exploitation
* Social networks analysis for collaborative recommendation
* User profile construction based on social tagging information
* Context-aware multimedia content access and delivery
* Mobile and ubiquitous multimedia content access and delivery

++++++++++++++++++++
Organizing Committee
++++++++++++++++++++

* Iván Cantador, Universidad Autónoma de Madrid, Spain
* Peter Mika, Yahoo! Research, Spain
* David Vallet, Universidad Autónoma de Madrid, Spain
* José C. Cortizo, Universidad Europea de Madrid, Spain
* Francisco M. Carrero, Universidad Europea de Madrid, Spain

+++++++++++++++++
Program Committee
+++++++++++++++++

* Sofia Angeletou, Knowledge Media Institute, The Open University, UK
* Ching-man Au Yeung, NTT Communication Science Labs, Japan
* Pablo Castells, Universidad Autónoma de Madrid, Spain
* Manuel Cebrián, Massachusetts Institute of Technology, USA
* Rosta Farzan, Carnegie Mellon University, USA
* Miriam Fernández, Knowledge Media Institute, The Open University, UK
* Enrique Frías, Telefónica I+D, Spain
* Ana García-Serrano, Universidad Nacional de Educación a Distancia, Spain
* Andrés García-Silva, Universidad Politécnica de Madrid, Spain
* Tom Heath, Talis, UK
* Frank Hopfgartner, University of Glasgow, UK
* Ioannis Konstas, University of Edinburgh, UK
* Estefanía Martín, Universidad Rey Juan Carlos, Spain
* Phivos Mylonas, National Technical University of Athens, Greece
* Daniel Olmedilla, Telefónica I+D, Spain
* Carlos Pedrinaci, Knowledge Media Institute, The Open University, UK
* Jérôme Picault, Alcatel-Lucent Bell Labs, France
* Francesco Ricci, Free University of Bozen-Bolzano, Italy
* Sergey A. Sosnovsky, University of Pittsburgh, USA
* Martin Szomszor, City University London, UK
* Marc Torrens, Strands, Spain
* Paulo Villegas, Telefónica I+D, Spain

++++++++++
Organizers
++++++++++

* Universidad Autónoma de Madrid, http://www.uam.es/
* Yahoo! Research, http://research.yahoo.com/
* Universidad Europea de Madrid, http://www.esp.uem.es/gsi/

++++++++
Sponsors
++++++++

* Ministerio de Ciencia e Innovación de España (CENIT-2007-1012), https://i3media.barcelonamedia.org/
* Consorcio MAVIR, http://www.mavir.net
* Sistema Madri+d, http://www.madrimasd.org

+++++++++++++++++++
Contact information
+++++++++++++++++++

Dr. Iván Cantador
Departamento de Ingeniería Informática
Escuela Politécnica Superior
Universidad Autónoma de Madrid, Spain
E-mail: ivan.cantador@uam.es
Phone: +34 91 497 2358

From Search to Recommender Systems

. Thursday, December 03, 2009
9 comments

Tech-companies rule the Web, and you can see that analyzing some of the biggest Internet companies like Google and Amazon. Google is the Intelligent Systems reference company due to their search engine, but also for the big quantity and quality of different technologies tehy develop like automated translation, user profiling, context management or even image processing.

Amazon is a e-commerce store, and it seems not so correlated with technology as Google, but the vision of Jeff Bezos and their commitment to technology have allowed them to grow like anyone before in the e-commerce market. For Bezos, an online store should not limit their catalog to a few items, online stores should contain millions of products, and should personalize the user experience of their users. His vision was clear: "if you have 3 million customers in the Web, I should have 3 million online stores", and then the recommender system ruled Amazon.

Both technologies (search and recommender systems) are useful for the Information Overload problem we suffer nowadays. But they're radically different from their conception. Search engines need the users to express their needs in textual form, and then process that query and retrieve the most relevant documents according to that query. Recommender Systems analyze the behaviour (and other kind of data) of the user in a website and then are able to choose the products or contents more likely to interest the user. Both approaches are useful, but until the moment recommender systems are not as popular as search engines.

But we are in a turnaround in the Web, as the way information is generated and consumed has changed. Nowadays, due to the success of Social Media sites like Facebook or Twitter, and even to the success of previous technologies as RSS, we receive a lot of information in a passive way: we don't ask directly to receive that information, but we receive it. Until the moment, the problem was to find some important information, but now the problem is turning into choose what information I already receive is relevant to me. That's why I think recommender systems will replace in popularity to search engines in the future.