Grant: Research Tools and Instruments - Category 1 (<$150,000)
University of Ottawa
$59,146.00
Experimental Platform for Big Data and Text Mining
EF 2013-14
Résumé
Our group of researchers from the University of Ottawa's Text Analysis and Machine Learning lab is involved in a research program on novel techniques for data mining and text mining from very large datasets available on the Web or from other sources (so-called ""big data""). Examples include mining social media texts (twitter messages, blogs, etc.), webpages, databases, and collections of scientific articles; predicting molecular interactions from very large datasets in bioinformatics; and analyzing graphs which represent enormous social networks. Our research objectives share a pattern of supporting experiments: it is necessary to explore the settings for multiple parameters used by different algorithms. The established evaluation methods also call for repeated runs with different training data sets and different test data sets. A multi-processor compute server and an accompanying data server are needed in order to enable efficient and feasible experiments of this scale. The current computer systems available to the researchers from our group are outdated and no longer satisfy our needs in terms of storage capacity, computing speed and amount of memory required to tackle data at such large scales which are common in the above mentioned applications. We are running some of our programs on the Canadian academic research computing networks. However, they impose limitations on accounts, such as dedicated and guaranteed CPU time for long-running processes and the amount, duration and type of available disk storage. As our experiments process and produce large amount of data and results, a mismatch occurs between our needs and what is offered on different nodes in terms of the computing power, memory capacity and architecture. Also, sometimes issues such as copyright, licensing and access restrictions imposed by data providers makes their use complicated, if not impossible, in such shared academic networks. Therefore, we need to have a local computing and storage capacity that will rise to the challenges faced by the faculty members of our group and their many graduate students, research assistants, and post-doctoral fellows.
Programme
Research Tools and Instruments - Category 1 (<$150,000)
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
458539-2014
Name nom
Inkpen, Diana
Department département
Electrical Engineering and Computer Science , School of
Organization id
28
Institution établissement
University of Ottawa
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2014
Award amount
59146
Program id
EQPEQ
Program name en
Research Tools and Instruments - Category 1 (<$150,000)
Program name fr
Outils et instruments de recherche - catégorie 1 (<150 000$)
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Partie
1
Nb partie
1
Application title
Experimental Platform for Big Data and Text Mining
Keyword
NSERC
Application summary
Our group of researchers from the University of Ottawa's Text Analysis and Machine Learning lab is involved in a research program on novel techniques for data mining and text mining from very large datasets available on the Web or from other sources (so-called ""big data""). Examples include mining social media texts (twitter messages, blogs, etc.), webpages, databases, and collections of scientific articles; predicting molecular interactions from very large datasets in bioinformatics; and analyzing graphs which represent enormous social networks. Our research objectives share a pattern of supporting experiments: it is necessary to explore the settings for multiple parameters used by different algorithms. The established evaluation methods also call for repeated runs with different training data sets and different test data sets. A multi-processor compute server and an accompanying data server are needed in order to enable efficient and feasible experiments of this scale. The current computer systems available to the researchers from our group are outdated and no longer satisfy our needs in terms of storage capacity, computing speed and amount of memory required to tackle data at such large scales which are common in the above mentioned applications. We are running some of our programs on the Canadian academic research computing networks. However, they impose limitations on accounts, such as dedicated and guaranteed CPU time for long-running processes and the amount, duration and type of available disk storage. As our experiments process and produce large amount of data and results, a mismatch occurs between our needs and what is offered on different nodes in terms of the computing power, memory capacity and architecture. Also, sometimes issues such as copyright, licensing and access restrictions imposed by data providers makes their use complicated, if not impossible, in such shared academic networks. Therefore, we need to have a local computing and storage capacity that will rise to the challenges faced by the faculty members of our group and their many graduate students, research assistants, and post-doctoral fellows.