tag:blogger.com,1999:blog-54915198053082685012011-11-27T23:44:40.913ZExplorations on current issues in opinion mining, knowledge discovery, tools and techniques.Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.comBlogger111100tag:blogger.com,1999:blog-5491519805308268501.post-79923842702204950092011-09-25T18:00:00.001+01:002011-09-25T23:19:51.375+01:00

Earlier this year I gave a presentation on Sentiment Classification at the 2011 RapidMiner User Conference in Dublin. I have posted the slides on Slideshare. RCOMM 2011 - Sentiment Classification View more presentations from bohanairl. There is an extended experiment based on what has been discussed in this blog, but now running on RapidMiner 5. The original word vector model is

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-44313585723305441052011-02-02T21:39:00.009Z2011-02-02T22:35:46.088Z

Lexicons are a big part of my current research in opinion mining. Aside from the potential of helping supervised learning methods, they can be applied to unsupervised techniques - an appealing idea for research whose goal is domain independence. An opinion lexicon is a database that associates terms with opinion information - normally in the form of a numeric score indicating a term's positive or

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-6388433087980969142009-09-08T21:36:00.017+01:002009-09-08T23:09:15.897+01:00

In a previous post we have discussed an example of how to perform text classification in RapidMiner, and we used a data set of film reviews against several word vector schemes to classify documents according to their overall positive or negative sentiment. In this tutorial we show how to look for better results by using RapidMiner's parameter testing feature and evaluate the effects of feature

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com12tag:blogger.com,1999:blog-5491519805308268501.post-58831647782370111712009-04-19T17:33:00.003+01:002009-04-19T17:39:47.933+01:00

Got that from From KDNuggets...A workshop dedicated to topic and opinion mining being held in Hong Kong later this year as part of ACM's CIKM '09, and has recently issued a CFP.Key dates as per the main page:Individual workshop papers due: July 20, 2009Notification of Acceptance: August 10, 2009Camera ready: August 15, 2009 *(hard deadline for publication in proceedings)*Early registration

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-3417207920964501042008-07-11T11:16:00.004+01:002008-07-11T14:58:25.939+01:00

In this video, Steve Whittaker from Sheffield University talks about recent research in the area of Digital Memories - storing information about personal events spanning an entire lifetime in digital format, with obvious opportunities for mining all kinds of interesting patterns. It can also open up a particular branch of mining applications specifically geared at providing personalized, easy to

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-86109318828216573602008-06-23T22:01:00.019+01:002008-07-01T23:29:57.496+01:00

In this post I'll use the polarity data set from Bo Pang / Lilian Lee to perform a text classification experiment on RapidMiner. RapidMiner (formerly Yale) is a open source data mining and knowledge discovery tool written in Java, incorporating most well known mining algorithms for classification, clustering and regression; it also contains plugins for specialized tasks such as text mining and

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com11tag:blogger.com,1999:blog-5491519805308268501.post-33248726345883768632008-05-10T22:19:00.008+01:002008-07-01T23:33:20.268+01:00

A repository with results on data mining experimentsThe Experiment Databases tool makes empirical results from AI data mining experiments more accessible and reusable. The site hosts a query engine in SQL format, retrieving results from mining experiments recorded into their repository. These can then be easily studied, and compared to other similar experiments - something that could otherwise

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com1tag:blogger.com,1999:blog-5491519805308268501.post-79782165686694378692008-05-10T21:44:00.007+01:002008-06-05T10:52:37.067+01:00

Here is a list of text data sets available on the web, with some comments on their content.1. UCI's Machine Learning Repository - A huge list of data sets on a variety of topics and formats in a searchable interface. There are 8 textual data sets available, including the popular Reuters 21578 and 20 NewsGroups data sets for text classification.2. TechTC Data Set is a repository of text documents

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com4tag:blogger.com,1999:blog-5491519805308268501.post-69927501343360122332007-11-25T21:56:00.000Z2007-11-26T00:01:34.698Z

Stunning array of projects in knowledge visualization, many of them exploring techniques for visualizing textual data and its relations to other data sources. A follow on from many mining exercises, it opens up far wider choices for humans to relate to the original raw content.

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-52487428899512393722007-11-25T18:57:00.000Z2007-11-28T23:49:56.204Z

After much reading and pondering, here's a shortlist of potential topics that nicely relate to text mining and knowledge management (Some references are missing):1- Investigate the problem of quantification (Forman, HP Labs) in text classification on a specific domain. Useful in estimating positive cases, concept drift etc.2- Improving classification performance with features from discourse

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0tag:blogger.com,1999:blog-5491519805308268501.post-55051264749217751192007-10-14T16:51:00.000+01:002007-10-14T21:35:06.054+01:00

Taken from Ljubliana's Summer School on Semantic Web '05. More lectures available on http://videolectures.netA lecture on applications of document summarization for generating semantic information in the form of graphs representing a given relationship on the text set.Learning Semantic Sub-graphs for Document Summarization, Marko GrobelnikInformation Extraction LectureInformation extraction,

Bruno Ohana, Dublin, Irelandhttp://www.blogger.com/profile/17485902015298972883noreply@blogger.com0