Natural Language Toolkit — NLTK 2.0 documentation Quantified Impressions Recommender system Recommender systems or recommendation systems (sometimes replacing "system" with a synonym such as platform or engine) are a subclass of information filtering system that seek to predict the 'rating' or 'preference' that user would give to an item. Recommender systems have become extremely common in recent years, and are applied in a variety of applications. The most popular ones are probably movies, music, news, books, research articles, search queries, social tags, and products in general. However, there are also recommender systems for experts, jokes, restaurants, financial services, life insurance, persons (online dating), and twitter followers . Overview The differences between collaborative and content-based filtering can be demonstrated by comparing two popular music recommender systems - Last.fm and Pandora Radio. Each type of system has its own strengths and weaknesses. Recommender system is an active research area in the data mining and machine learning areas.
Adaptive Semantics Inc. New York Times - Linked Open Data Language Computer - Cicero On-Demand API The Cicero On-Demand provides a RESTful interface that wraps LCC's CiceroLite and other NLP components. This API is used for Cicero On-Demand whether the server is the one hosted at LCC or is run locally on your machine. You can access a free, rate-limited version online, as described below, at demo.languagecomputer.com. For more information on service plans, contact support. Following is a description of the REST calls, which are valid for both the hosted and local modes. Checking the server status You can verify the server is running via the built-in HTML viewer. Accessing the server using a web browser You can access the server directly using a web browser. Accessing the server using Curl. Curl is a command line utility that lets you access web services. To process a local file using Curl To process raw text using Curl Specifying an output format on Windows:
Multi-Lingual Text Analysis- A Plan To Action from #SMAS12 ‘80% of success is showing up’- Woody Allen He could have been referring to multi-lingual text analysis. Is that good news? It might be. Native language text analysis is complex but it’s not impossible. This was a remarkable point from last week’s Social Media Analytics Summit (#SMAS12) from Text Analytics News. Consider the data from the 2010 US Census: 20% of the population (over the age of 5) speaks a language other than English at home35 million – US residents speak Spanish in the home50% of US population growth is coming from HispanicsAsian Americans are the fastest growing population segment- 46% increase 2000 vs 20102.6 million- US residents speak Chinese in the homeNon-native speakers prefer to conduct business in their native language This is a business and a cultural issue. How? Start with a cross-lingual solution that works in the native language of the text. Work backwards. Make a plan, and stick with the plan. Is your business ready to meet the challenge?
Recommendation’s Engine based on Spread Activation algorithm « Álvaro Brange’s Blog. September 7, 2010 Suggestion graph made with test application Hi, Since last year that I haven’t added any post on my blog, but I would like add new posts. This year I’ll start sharing publishing the work carried out in order to get my degree. Here is the abstract: Nowadays people are reproducing the social network from your real life into a virtual space in which are represented the same social structures and relations of friendship, work, academic partners, and “love- relationships”. Read full document Regards, Álvaro Like this: Like Loading... IBM Sentiment Analysis A technique to detect favorable and unfavorable opinions toward specific subjects (such as organizations and their products) within large numbers of documents offers enormous opportunities for various applications. It would provide powerful functionality for competitive analysis, marketing analysis, and detection of unfavorable rumors for risk management. Our sentiment analysis approach is to extract sentiments associated with polarities of positive or negative for specific subjects from a document, instead of classifying the whole document into positive or negative.
Elsevier Sponsors 2010 Semantic Web Challenge NEW YORK, November 16, 2010 /PRNewswire-FirstCall/ -- - Winners Announced at International Semantic Web Conference Elsevier announced the winners of the 2010 Semantic Web Challenge. The Elsevier sponsored Challenge occurred at the International Semantic Web Conference held in Shanghai, China from 7-11 November, 2010. The semantic web is an exciting new direction in Artificial Intelligence, aiming to add meaning to information on a web-size scale. Over the last eight years, the Challenge has attracted more than 140 entries. Organized this year by Christian Bizer from the Freie Universitat Berlin, Germany, and Diana Maynard from the University of Sheffield, UK, the Semantic Web Challenge consists of two categories: "Open Track" and "Billion Triples Track." The winners of the 2010 Open Track challenge were the team from Stanford University comprising of Clement Jonquet, Paea LePendu, Sean M. NCBO Resource Index: Ontology - Based Search and Mining of Biomedical Resources Paper: About the prize