Menno van Zaanen
Research Subjects
Research Interests
Menno van Zaanen has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Johannes Sibeko
Nelson Mandela University
3 shared publications - Luuk Van Waes
Department of Management, University of Antwerp, 2000 Antwerp, Belgium
3 shared publications - Rianne Conijn
Eindhoven University of Technology
3 shared publications - Alexandra Sierra Rativa
Erasmus University Rotterdam
2 shared publications - Anelda Van Der Walt
Talarify
2 shared publications - Martin Atzmueller
Osnabrück University
2 shared publications
Latest Publications
- Open Access
- 31 December 2025
- Published by Digital Humanities Association of Southern Africa in Journal of the Digital Humanities Association of Southern Africa (DHASA)
- Vol. 6 (2)
Stop words in Khoekhoe
Stop word lists are useful resources that allow for the filtering of words in texts that typically do not carry (much) content. Filtering stop words can improve the efficiency and accuracy of data processing. Stop words are typically short and occur very frequently in texts. Stop word lists are language dependent and many low-resource languages currently do not have (accurate) stop word lists. In this article, we look at how we can create, based on word frequency, a stop word list for Khoekhoe, which is a low-resource language spoken in Southern Africa. Given that stop words do not carry much content, they can be expected to occur consistently across different texts. We compare lists of most frequent words between texts in different genres and which words feature in these lists consistently. We look at the overlap of frequent words in English texts and compare these to a known English stop word list as well, and compare the results with the overlap of frequent words in Khoekhoe texts. The results show that there is a high overlap between genres for English, but the overlap between the Khoekhoe genres is lower. This may be due to a different typological profile of Khoekhoe. This means that creating a stop word list for Khoekhoe is more complicated and most likely requires other techniques to produce a useful stop word list.
- 31 December 2025
- Published by Digital Humanities Association of Southern Africa in Journal of the Digital Humanities Association of Southern Africa (DHASA)
- Vol. 6 (2)
Open AccessStop words in Khoekhoe
Stop word lists are useful resources that allow for the filtering of words in texts that typically do not carry (much) content. Filtering stop words can improve the efficiency and accuracy of data processing. Stop words are typically short and occur very frequently in texts. Stop word lists are language dependent and many low-resource languages currently do not have (accurate) stop word lists. In this article, we look at how we can create, based on word frequency, a stop word list for Khoekhoe, which is a low-resource language spoken in Southern Africa. Given that stop words do not carry much content, they can be expected to occur consistently across different texts. We compare lists of most frequent words between texts in different genres and which words feature in these lists consistently. We look at the overlap of frequent words in English texts and compare these to a known English stop word list as well, and compare the results with the overlap of frequent words in Khoekhoe texts. The results show that there is a high overlap between genres for English, but the overlap between the Khoekhoe genres is lower. This may be due to a different typological profile of Khoekhoe. This means that creating a stop word list for Khoekhoe is more complicated and most likely requires other techniques to produce a useful stop word list.
- Open Access
- 31 December 2025
- Published by Digital Humanities Association of Southern Africa in Journal of the Digital Humanities Association of Southern Africa (DHASA)
- Vol. 6 (2)
An exploration of the computational identification of English loan words in Sesotho
South Africa, with its twelve official languages, is an inherently multilingual country. As such, speakers of many of the languages have been in direct contact. This has led to a cross-over of words and phrases between languages. In this article, we provide a methodology to identify words that are (potentially) borrowed from another language. We test our approach by trying to identify words that moved from English into Sesotho (or potentially the other way around). To do this, we start with a bilingual Sesotho-English dictionary (Bukantswe). We then develop a lexicographic comparison method that takes a pair of lexical items (English and Sesotho) and computes a range of distance metrics. These distance metrics are applied to the raw words (i.e., comparing orthography), but using the Soundex algorithm, an approximate phonological comparison can be made as well. Unfortunately, Bukantswe does not contain complete annotation of loan words, so a quantitative evaluation is not currently possible. We provide a qualitative analysis of the results, which shows that many loan words can be found, but in some cases lexical items that have a high similarity are not loan words. We discuss different situations related to the influence of orthography, phonology, syllable structure, and morphology. The approach itself is language independent, so it can also be applied to other language pairs, e.g., Afrikaans and Sesotho, or more related languages, suchas isiXhosa and isiZulu.
- 31 December 2025
- Published by Digital Humanities Association of Southern Africa in Journal of the Digital Humanities Association of Southern Africa (DHASA)
- Vol. 6 (2)
Open AccessAn exploration of the computational identification of English loan words in Sesotho
South Africa, with its twelve official languages, is an inherently multilingual country. As such, speakers of many of the languages have been in direct contact. This has led to a cross-over of words and phrases between languages. In this article, we provide a methodology to identify words that are (potentially) borrowed from another language. We test our approach by trying to identify words that moved from English into Sesotho (or potentially the other way around). To do this, we start with a bilingual Sesotho-English dictionary (Bukantswe). We then develop a lexicographic comparison method that takes a pair of lexical items (English and Sesotho) and computes a range of distance metrics. These distance metrics are applied to the raw words (i.e., comparing orthography), but using the Soundex algorithm, an approximate phonological comparison can be made as well. Unfortunately, Bukantswe does not contain complete annotation of loan words, so a quantitative evaluation is not currently possible. We provide a qualitative analysis of the results, which shows that many loan words can be found, but in some cases lexical items that have a high similarity are not loan words. We discuss different situations related to the influence of orthography, phonology, syllable structure, and morphology. The approach itself is language independent, so it can also be applied to other language pairs, e.g., Afrikaans and Sesotho, or more related languages, suchas isiXhosa and isiZulu.
- 11 December 2025
- Published by Ubiquity Press, Ltd. in Journal of Open Humanities Data
- Vol. 11
Annotated Mystery Narratives Data Set
- 11 December 2025
- Published by Ubiquity Press, Ltd. in Journal of Open Humanities Data
- Vol. 11
Annotated Mystery Narratives Data Set
- Open Access
- 20 September 2024
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (2) , 1577-1592
Developing and testing syllabification systems for South African Sesotho
In this article, we describe the development of two syllabification systems for South African Sesotho. First, we implemented a rule-based syllabification system based on the syllabification rules proposed by Guma (An outline structure of Southern Sotho, 2nd edn, Shooter and Shuter Publishers, Pietermaritzburg, 1982). The rules describe the location of syllable boundaries based on the location of vowels, consonants, simple and complex nasal consonants, and the lateral l. Second, we used TeX’s pattern-based hyphenation system as a syllabification system. This pattern-based system was trained on syllabified words from a dictionary as identified in Chitja (Phatlamantsoe ya Sesotho ya Machaba, Mazenod Publishers, Lesotho, 2010). The syllable boundaries in the words from the dictionary were manually checked and, where needed, adjusted to maintain a consistent orthography. Both systems were evaluated on 13,551 tokens using ten-fold cross-validation (as the pattern-based system requires training data). The rule-based system shows a 99.69% word level accuracy, which indicates that Sesotho syllabification is highly regular. The pattern-based system leads to 78.97% accuracy. This lower score is likely related to the limitations in the placement of boundaries in the TeX system. A qualitative analysis of the results shows some (unresolved) inconsistencies in the dictionary entries, in particular related to the conversion of the Lesotho Sesotho orthography to the South African Sesotho orthography and the handling of loan words.
- 20 September 2024
- Published by Springer Nature in Language Resources and Evaluation
- Vol. 59 (2) , 1577-1592
Open AccessDeveloping and testing syllabification systems for South African Sesotho
In this article, we describe the development of two syllabification systems for South African Sesotho. First, we implemented a rule-based syllabification system based on the syllabification rules proposed by Guma (An outline structure of Southern Sotho, 2nd edn, Shooter and Shuter Publishers, Pietermaritzburg, 1982). The rules describe the location of syllable boundaries based on the location of vowels, consonants, simple and complex nasal consonants, and the lateral l. Second, we used TeX’s pattern-based hyphenation system as a syllabification system. This pattern-based system was trained on syllabified words from a dictionary as identified in Chitja (Phatlamantsoe ya Sesotho ya Machaba, Mazenod Publishers, Lesotho, 2010). The syllable boundaries in the words from the dictionary were manually checked and, where needed, adjusted to maintain a consistent orthography. Both systems were evaluated on 13,551 tokens using ten-fold cross-validation (as the pattern-based system requires training data). The rule-based system shows a 99.69% word level accuracy, which indicates that Sesotho syllabification is highly regular. The pattern-based system leads to 78.97% accuracy. This lower score is likely related to the limitations in the placement of boundaries in the TeX system. A qualitative analysis of the results shows some (unresolved) inconsistencies in the dictionary entries, in particular related to the conversion of the Lesotho Sesotho orthography to the South African Sesotho orthography and the handling of loan words.
- Open Access
- 16 February 2024
- Published by Digital Humanities Association of Southern Africa
- Vol. 5 (1)
Introduction to the Special Issue: “Digital Humanities for Inclusion”
It is with immense pride and anticipation that we introduce the fifth volume of the Journal of Digital Humanities Association of Southern Africa (JDHASA), centred on the theme “Digital Humanities for Inclusion.”
- 16 February 2024
- Published by Digital Humanities Association of Southern Africa
- Vol. 5 (1)
Open AccessIntroduction to the Special Issue: “Digital Humanities for Inclusion”
It is with immense pride and anticipation that we introduce the fifth volume of the Journal of Digital Humanities Association of Southern Africa (JDHASA), centred on the theme “Digital Humanities for Inclusion.”
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 55-66
Annotating Mystery Novels: Guidelines and Adaptations
Nuette Heyns, Menno Van Zaanen. Proceedings of the The 6th Workshop on Narrative Understanding. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 55-66
Open AccessAnnotating Mystery Novels: Guidelines and Adaptations
Nuette Heyns, Menno Van Zaanen. Proceedings of the The 6th Workshop on Narrative Understanding. 2024.
- Open Access
Multi-Level Analysis of Learning Management Systems’ User Acceptance Exemplified in Two System Case Studies
There has recently been an increasing interest in Learning Management Systems (LMSs). It is currently unclear, however, exactly how these systems are perceived by their users. This article analyzes data on user acceptance for two LMSs (Blackboard and Canvas). The respective data are collected using a questionnaire modeled after the Technology Acceptance Model (TAM); it relates several variables that influence system acceptability, allowing for a detailed analysis of the system acceptance. We present analyses at two levels of the questionnaire data: questions and constructs (taken from TAM) as well as on different analysis levels using targeted methods. First, we investigate the differences between the above LMSs using statistical tests (t-test). Second, we provide results at the question level using descriptive indices, such as the mean and the Gini heterogeneity index, and apply methods for ordinal data using the Cumulative Link Mixed Model (CLMM). Next, we apply the same approach at the TAM construct level plus descriptive network analysis (degree centrality and bipartite motifs) to explore the variability of users’ answers and the degree of users’ satisfaction considering the extracted patterns. In the context of TAM, the statistical model is able to analyze LMS acceptance on the question level. As we are also very much interested in identifying LMS acceptance at the construct level, in this article, we provide both statistical analysis as well as network analysis to explore the connection between questionnaire data and relational data. A network analysis approach is particularly useful when analyzing LMS acceptance on the construct level, as this can take the structure of the users’ answers across questions per construct into account. Taken together, these results suggest a higher rate of user acceptance among Canvas users compared to Blackboard both for the question and construct level. Likewise, the descriptive network modeling for Canvas indicates a slightly higher concordance between Canvas users than Blackboard at the construct level.
Open AccessMulti-Level Analysis of Learning Management Systems’ User Acceptance Exemplified in Two System Case Studies
There has recently been an increasing interest in Learning Management Systems (LMSs). It is currently unclear, however, exactly how these systems are perceived by their users. This article analyzes data on user acceptance for two LMSs (Blackboard and Canvas). The respective data are collected using a questionnaire modeled after the Technology Acceptance Model (TAM); it relates several variables that influence system acceptability, allowing for a detailed analysis of the system acceptance. We present analyses at two levels of the questionnaire data: questions and constructs (taken from TAM) as well as on different analysis levels using targeted methods. First, we investigate the differences between the above LMSs using statistical tests (t-test). Second, we provide results at the question level using descriptive indices, such as the mean and the Gini heterogeneity index, and apply methods for ordinal data using the Cumulative Link Mixed Model (CLMM). Next, we apply the same approach at the TAM construct level plus descriptive network analysis (degree centrality and bipartite motifs) to explore the variability of users’ answers and the degree of users’ satisfaction considering the extracted patterns. In the context of TAM, the statistical model is able to analyze LMS acceptance on the question level. As we are also very much interested in identifying LMS acceptance at the construct level, in this article, we provide both statistical analysis as well as network analysis to explore the connection between questionnaire data and relational data. A network analysis approach is particularly useful when analyzing LMS acceptance on the construct level, as this can take the structure of the users’ answers across questions per construct into account. Taken together, these results suggest a higher rate of user acceptance among Canvas users compared to Blackboard both for the question and construct level. Likewise, the descriptive network modeling for Canvas indicates a slightly higher concordance between Canvas users than Blackboard at the construct level.
- Open Access
- 8 February 2023
- Published by Taylor & Francis
- p. 56-66
Challenges and Opportunities of Digital Humanities Training in South Africa
With Digital Humanities (DH) in South Africa (SA) still a relatively “new” and unexplored research area, a more comprehensive approach to creating awareness and training is required. In the past, the fields of Humanities and Social Sciences (HSS) were typically excluded from discussions around data science-related research infrastructure and Human Capacity Development (HCD) and while initial DH-related activities started around the turn of the millennium in SA, mostly in isolated pockets, the general uptake has been rather slow. This can partially be attributed to the absence of a community of practice (CoP) to support especially researchers from the Humanities and Social Sciences interested in adopting computational methodologies and accessing contextually useful training material. This chapter briefly reflects on DH-related training events run in the region, their impact, and the development of a subsequent program informed by what was learned. In particular, we describe two different, but related initiatives: The Carpentries and ESCALATOR. The Carpentries is an international non-profit organization that teaches computational skills training events that require little prior computational experience. ESCALATOR is a program supported by the South African Centre for Digital Language Resources (SADiLaR) and collaboratively developed with Talarify, which aims to develop CoP’s for the area of Digital Humanities in the country. This program stems from the identified limitations of running ad hoc training events, which were taught at multiple different universities to provide broad coverage throughout the country. This chapter describes a range of challenges and potential solutions related to the training of researchers in South Africa, such as limited resources (related to Internet access, computational power, and electricity supply), communication challenges (consistent and timely reaching of researchers interested in training programs), etc. The lessons learned gave the ESCALATOR program a solid start to address certain challenges from the start.
- 8 February 2023
- Published by Taylor & Francis
- p. 56-66
Open AccessChallenges and Opportunities of Digital Humanities Training in South Africa
With Digital Humanities (DH) in South Africa (SA) still a relatively “new” and unexplored research area, a more comprehensive approach to creating awareness and training is required. In the past, the fields of Humanities and Social Sciences (HSS) were typically excluded from discussions around data science-related research infrastructure and Human Capacity Development (HCD) and while initial DH-related activities started around the turn of the millennium in SA, mostly in isolated pockets, the general uptake has been rather slow. This can partially be attributed to the absence of a community of practice (CoP) to support especially researchers from the Humanities and Social Sciences interested in adopting computational methodologies and accessing contextually useful training material. This chapter briefly reflects on DH-related training events run in the region, their impact, and the development of a subsequent program informed by what was learned. In particular, we describe two different, but related initiatives: The Carpentries and ESCALATOR. The Carpentries is an international non-profit organization that teaches computational skills training events that require little prior computational experience. ESCALATOR is a program supported by the South African Centre for Digital Language Resources (SADiLaR) and collaboratively developed with Talarify, which aims to develop CoP’s for the area of Digital Humanities in the country. This program stems from the identified limitations of running ad hoc training events, which were taught at multiple different universities to provide broad coverage throughout the country. This chapter describes a range of challenges and potential solutions related to the training of researchers in South Africa, such as limited resources (related to Internet access, computational power, and electricity supply), communication challenges (consistent and timely reaching of researchers interested in training programs), etc. The lessons learned gave the ESCALATOR program a solid start to address certain challenges from the start.