Walter Daelemans
Biographic Data
| ID | 4385402 |
|---|---|
| NAME | Walter Daelemans |
| GIVEN NAMES | Walter |
| FAMILY NAME | Daelemans |
| SIGNATURE | DAELEMANS W |
| AFFILIATIONS | University of Antwerp |
| ORCID | 0000-0002-9832-7890 |
| VERIFIED | Yes |
| TOTAL WORKS | 13 |
| TOTAL CITATIONS | 11 |
| AUTHOR COUNT | 13 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2001 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 2 |
Journal article classification using abstracts
Communicating across educational boundaries
This paper studies linguistic accommodation patterns in a large corpus of private online conversations produced by Flemish secondary school students. We use Poisson models to examine whether the teenagers adjust their writing style depending on their interlocutor’s educational profile, while also taking into account the extent to which these adaptation patterns are influenced by the authors’ own educational background or by other aspects of their…
A reputational perspective on structural reforms
Despite recurrent observations that media reputations of agencies matter to understand their reform experiences, no studies have theorized and tested the role of sentiment. This study uses novel and advanced BERT language models to detect attributions of responsibility for positive/negative outcomes in media coverage towards 14 Flemish (Belgian) agencies between 2000 and 2015 through supervised machine learning, and connects these data to the Bel…
Agencies on the parliamentary radar
The news media frame political debate about public agencies, and enable legislators with incomplete information to monitor and act upon agency (mal)performance. While studies show that the news media matters for parliamentary attention, the contingent nature of this relation has been understudied. Building on agenda‐setting theory, this study theorizes that the effect of newspaper coverage is contingent on the sentiment of coverage, the majority …
Detecting contrast patterns in newspaper articles by combining discourse analysis and text mining
Text mining aims at constructing classification models and finding interesting patterns in large text collections. This paper investigates the utility of applying these techniques to media analysis, more specifically to support discourse analysis of news reports about the 2007 Kenyan elections and post-election crisis in local (Kenyan) and Western (British and US) newspapers. It illustrates how text mining methods can assist discourse analysis by…
Advances in Digital Music Iconography
In this paper, we present MINERVA, the first benchmark dataset for the detection of musical instruments in non-photorealistic, unrestricted image collections from the realm of the visual arts. This effort is situated against the scholarly background of music iconography, an interdisciplinary field at the intersection of musicology and art history. We benchmark a number of state-of-the-art systems for image classification and object detection. Our…
Modeling Adolescents’ Online Writing Practices
The paper discusses four generalized linear mixed models fitted to capture distinct patterns of non-standard writing practices in Flemish adolescents’ social media messages. Apart from a general model that predicts the count of all “deviations” from the Dutch formal writing standard, additional models were fitted for specific types of non-standard features. These types relate to the so-called chatspeak “maxims” of orality, brevity and expressive …
Lexical Patterns in Adolescents’ Online Writing
This article examines the impact of the sociodemographic profile (including age, gender, and educational track) of Flemish adolescents (aged 13–20) on lexical aspects of their informal online discourse. The focus on lexical and more “traditional,” print-based aspects of literacy is meant to complement previous research on sociolinguistic variation with respect to the use of prototypical features of social media writing. Drawing on a corpus of 434…
Implicit Schemata and Categories in Memory-based Language Processing
Memory-based language processing (MBLP) is an approach to language processing based on exemplar storage during learning and analogical reasoning during processing. From a cognitive perspective, the approach is attractive as a model for human language processing because it does not make any assumptions about the way abstractions are shaped, nor any a priori distinction between regular and exceptional exemplars, allowing it to explain fluidity of l…
Cross-Genre Authorship Verification Using Unmasking
In this paper we will stress-test a recently proposed technique for computational authorship verification, ‘‘unmasking'', which has been well received in the literature. The technique envisages an experimental set-up commonly referred to as ‘‘authorship verification'', a task generally deemed more difficult than so-called ‘‘authorship attribution''. We will apply the technique to authorship verification across genres, an extremely complex text ca…
Recent Advances in Example-Based Machine Translation
example, where the machine side requires some standard expressions in order to execute certain machine actions.Language translation is one of the most complicated tasks of the human brain, which utilizes not only linguistic knowledge but also knowledge of the world, and varieties of our sophisticated human senses.EBMT is one of the possible approaches to the mechanism of human translation, and this book represents a considerable contribution to t…
Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems
We examine how differences in language models, learned by different data-driven systems performing the same NLP task, can be exploited to yield a higher accuracy than the best individual system. We do this by means of experiments involving the task of morphosyntactic word class tagging, on the basis of three different tagged corpora. Four well-known tagger generators (hidden Markov model, memory-based, transformation rules, and maximum entropy) a…
Title Index
Cross-Genre Authorship Verification Using Unmasking
In this paper we will stress-test a recently proposed technique for computational authorship verification, ‘‘unmasking'', which has been well received in the literature. The technique envisages an experimental set-up commonly referred to as ‘‘authorship verification'', a task generally deemed more difficult than so-called ‘‘authorship attribution''. We will apply the technique to authorship verification across genres, an extremely complex text ca…
Implicit Schemata and Categories in Memory-based Language Processing
Memory-based language processing (MBLP) is an approach to language processing based on exemplar storage during learning and analogical reasoning during processing. From a cognitive perspective, the approach is attractive as a model for human language processing because it does not make any assumptions about the way abstractions are shaped, nor any a priori distinction between regular and exceptional exemplars, allowing it to explain fluidity of l…
Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems
We examine how differences in language models, learned by different data-driven systems performing the same NLP task, can be exploited to yield a higher accuracy than the best individual system. We do this by means of experiments involving the task of morphosyntactic word class tagging, on the basis of three different tagged corpora. Four well-known tagger generators (hidden Markov model, memory-based, transformation rules, and maximum entropy) a…
A reputational perspective on structural reforms
Despite recurrent observations that media reputations of agencies matter to understand their reform experiences, no studies have theorized and tested the role of sentiment. This study uses novel and advanced BERT language models to detect attributions of responsibility for positive/negative outcomes in media coverage towards 14 Flemish (Belgian) agencies between 2000 and 2015 through supervised machine learning, and connects these data to the Bel…
Agencies on the parliamentary radar
The news media frame political debate about public agencies, and enable legislators with incomplete information to monitor and act upon agency (mal)performance. While studies show that the news media matters for parliamentary attention, the contingent nature of this relation has been understudied. Building on agenda‐setting theory, this study theorizes that the effect of newspaper coverage is contingent on the sentiment of coverage, the majority …
Recent Advances in Example-Based Machine Translation
example, where the machine side requires some standard expressions in order to execute certain machine actions.Language translation is one of the most complicated tasks of the human brain, which utilizes not only linguistic knowledge but also knowledge of the world, and varieties of our sophisticated human senses.EBMT is one of the possible approaches to the mechanism of human translation, and this book represents a considerable contribution to t…
Improving Accuracy in Word Class Tagging through the Combination of Machine Learning Systems
We examine how differences in language models, learned by different data-driven systems performing the same NLP task, can be exploited to yield a higher accuracy than the best individual system. We do this by means of experiments involving the task of morphosyntactic word class tagging, on the basis of three different tagged corpora. Four well-known tagger generators (hidden Markov model, memory-based, transformation rules, and maximum entropy) a…
Title Index
Recent Advances in Example-Based Machine Translation
example, where the machine side requires some standard expressions in order to execute certain machine actions.Language translation is one of the most complicated tasks of the human brain, which utilizes not only linguistic knowledge but also knowledge of the world, and varieties of our sophisticated human senses.EBMT is one of the possible approaches to the mechanism of human translation, and this book represents a considerable contribution to t…
Cross-Genre Authorship Verification Using Unmasking
In this paper we will stress-test a recently proposed technique for computational authorship verification, ‘‘unmasking'', which has been well received in the literature. The technique envisages an experimental set-up commonly referred to as ‘‘authorship verification'', a task generally deemed more difficult than so-called ‘‘authorship attribution''. We will apply the technique to authorship verification across genres, an extremely complex text ca…
Implicit Schemata and Categories in Memory-based Language Processing
Memory-based language processing (MBLP) is an approach to language processing based on exemplar storage during learning and analogical reasoning during processing. From a cognitive perspective, the approach is attractive as a model for human language processing because it does not make any assumptions about the way abstractions are shaped, nor any a priori distinction between regular and exceptional exemplars, allowing it to explain fluidity of l…
Modeling Adolescents’ Online Writing Practices
The paper discusses four generalized linear mixed models fitted to capture distinct patterns of non-standard writing practices in Flemish adolescents’ social media messages. Apart from a general model that predicts the count of all “deviations” from the Dutch formal writing standard, additional models were fitted for specific types of non-standard features. These types relate to the so-called chatspeak “maxims” of orality, brevity and expressive …
Lexical Patterns in Adolescents’ Online Writing
This article examines the impact of the sociodemographic profile (including age, gender, and educational track) of Flemish adolescents (aged 13–20) on lexical aspects of their informal online discourse. The focus on lexical and more “traditional,” print-based aspects of literacy is meant to complement previous research on sociolinguistic variation with respect to the use of prototypical features of social media writing. Drawing on a corpus of 434…
Advances in Digital Music Iconography
In this paper, we present MINERVA, the first benchmark dataset for the detection of musical instruments in non-photorealistic, unrestricted image collections from the realm of the visual arts. This effort is situated against the scholarly background of music iconography, an interdisciplinary field at the intersection of musicology and art history. We benchmark a number of state-of-the-art systems for image classification and object detection. Our…
Detecting contrast patterns in newspaper articles by combining discourse analysis and text mining
Text mining aims at constructing classification models and finding interesting patterns in large text collections. This paper investigates the utility of applying these techniques to media analysis, more specifically to support discourse analysis of news reports about the 2007 Kenyan elections and post-election crisis in local (Kenyan) and Western (British and US) newspapers. It illustrates how text mining methods can assist discourse analysis by…
Agencies on the parliamentary radar
The news media frame political debate about public agencies, and enable legislators with incomplete information to monitor and act upon agency (mal)performance. While studies show that the news media matters for parliamentary attention, the contingent nature of this relation has been understudied. Building on agenda‐setting theory, this study theorizes that the effect of newspaper coverage is contingent on the sentiment of coverage, the majority …
Communicating across educational boundaries
This paper studies linguistic accommodation patterns in a large corpus of private online conversations produced by Flemish secondary school students. We use Poisson models to examine whether the teenagers adjust their writing style depending on their interlocutor’s educational profile, while also taking into account the extent to which these adaptation patterns are influenced by the authors’ own educational background or by other aspects of their…
A reputational perspective on structural reforms
Despite recurrent observations that media reputations of agencies matter to understand their reform experiences, no studies have theorized and tested the role of sentiment. This study uses novel and advanced BERT language models to detect attributions of responsibility for positive/negative outcomes in media coverage towards 14 Flemish (Belgian) agencies between 2000 and 2015 through supervised machine learning, and connects these data to the Bel…
Journal article classification using abstracts
Computer Science (11 works) · Artificial Intelligence (6 works) · Linguistics (6 works) · Topic Modeling (6 works) · Natural language processing (4 works) · Natural Language Processing Techniques (4 works) · Psychology (4 works) · Digital Communication and Language (3 works) · Flemish (3 works) · Focus (optics (3 works)