Searched for: author:"Raaijmakers, S.A."
(1 - 13 of 13)
document
den Hollander, R.J.M. (author), Adhikari, A. (author), Tolios, I. (author), van Bekkum, M. (author), Bal, A. (author), Hendriks, S. (author), Kruithof, M.C. (author), Gross, D. (author), Jansen, N. (author), Perez, G. (author), Buurman, K. (author), Raaijmakers, S.A. (author)
conference paper 2020
document
Raaijmakers, S.A. (author), Sappelli, M. (author), Kraaij, W. (author)
In this short paper, we address the interpretability of hidden layer representations in deep text mining: deep neural networks applied to text mining tasks. Following earlierwork predating deep learning methods, we exploit the internal neural network activation (latent) space as a source for performing k-nearest neighbor search, looking for...
conference paper 2017
document
Bouma, H. (author), Raaijmakers, S.A. (author), Halma, A.H.R. (author), Wedemeijer, H. (author)
Many threats in the real world can be related to activity of persons on the internet. Internet surveillance aims to predict and prevent attacks and to assist in finding suspects based on information from the web. However, the amount of data on the internet rapidly increases and it is time consuming to monitor many websites. In this paper, we...
conference paper 2012
document
Boertjes, E.M. (author), Gerrits, B.M. (author), Kooij, R.E. (author), van Maanen, P.P. (author), Raaijmakers, S.A. (author), de Wit, J.J. (author)
In this paper we describe the development of a model for measuring consumer trust in certain topics on the basis of social media. Specifically, we propose a model for trust that takes into account both textually expressed sentiment and source authority, and illustrate it on a specific case: the iCloud cloud computing service of Apple and its...
conference paper 2012
document
Koldijk, S.J. (author), van Staalduinen, M. (author), Raaijmakers, S.A. (author), van Rooij, I. (author), Kraaij, W. (author)
With an increased societal focus on a sustainable economy and a healthy population, well-being of knowledge workers has become an important topic. This paper investigates techniques to support a knowledge worker to manage his well-being. A possible solution is to monitor the workers’ behaviour and use this information for giving feedback as soon...
conference paper 2011
document
Verberne, S. (author), van Halteren, H. (author), Theijssen, D. (author), Raaijmakers, S.A. (author), Boves, L. (author)
In this paper, we evaluate a number of machine learning techniques for the task of ranking answers to why-questions. We use TF-IDF together with a set of 36 linguistically motivated features that characterize questions and answers. We experiment with a number of machine learning techniques (among which several classifiers and regression...
article 2011
document
Vonder, M.R. (author), van der Waaij, B.D. (author), Zwier, E. (author), Boertjes, E.M. (author), Oostveen, J.C. (author), Raaijmakers, S.A. (author), Schavemaker, J.G.M. (author), Schutte, K. (author), Meulenhoff, P.J. (author), van der Mark, W. (author)
Door de voortschrijdende technologische ontwikkelingen van sensor technologie en de groeiende complexiteit van onze samenleving, is er een duidelijke behoefte ontstaan om (meer) inzicht te krijgen in bestaande situaties en/of objecten. Om te voorkomen dat er een overload aan sensor data ontstaat is automatische ondersteuning van de interpretatie...
report 2011
document
Raaijmakers, S.A. (author), Kraaij, W. (author), TNO Informatie- en Communicatietechnologie (author)
Textual sentiment classifiers classify texts into a fixed number of affective classes, such as positive, negative or neutral sentiment, or subjective versus objective information. It has been observed that sentiment classifiers suffer from a lack of generalization capability: a classifier trained on a certain domain generally performs worse on...
conference paper 2010
document
Raaijmakers, S.A. (author), TNO Informatie- en Communicatietechnologie (author)
doctoral thesis 2009
document
Kraaij, W. (author), Raaijmakers, S.A. (author), Elzinga, P. (author), TNO Informatie- en Communicatietechnologie (author)
We propose a novel and intuitive way to quantify the utility of a classifier in cases where automatic classification is deployed as partial replacement of human effort, but accuracy requirements exceed the capabilities of the classifier at hand. in our approach, a binary classifier is combined with a meta-classifier mapping all decisions of the...
conference paper 2008
document
Raaijmakers, S.A. (author), Truong, K.P. (author), Wilson, T. (author), TNO Informatie- en communicatietechnologie TNO Defensie en Veiligheid (author)
We investigate the combination of several sources of information for the purpose of subjectivity recognition and polarity classification in meetings. We focus on features from two modalities, transcribed words and acoustics, and we compare the performance of three different textual representations: words, characters, and phonemes. Our...
conference paper 2008
document
Raaijmakers, S.A. (author), Kraaij, W. (author), TNO Informatie- en Communicatietechnologie (author), ICT (author)
We present a shallow linguistic approach to subjectivity classification. Using multinomial kernel machines, we demonstrate that a data representation based on counting character n-grams is able to improve on results previously attained on the MPQA corpus using word-based n-grams and syntactic information. We compare two types of string-based...
conference paper 2008
document
Wilson, T. (author), Raaijmakers, S.A. (author), TNO Informatie- en communicatietechnologie (author)
In this paper, we compare the performance of classifiers trained using word n-grams, character n-grams, and phoneme n-grams for recognizing subjective utterances in multiparty conversation. We show that there is value in using very shallow linguistic representations, such as character n-grams, for recognizing subjective utterances, in particular...
conference paper 2008
Searched for: author:"Raaijmakers, S.A."
(1 - 13 of 13)