Exploring West African Folk Narrative Texts Using Machine Learning
This paper examines how machine learning (ML) and natural language processing (NLP) can be used to identify, analyze, and generate West African folk tales. Two corpora of West African and Western European folk tales are compiled and used in three experiments on cross-cultural folk tale analysis. In...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/11/5/236 |
| _version_ | 1797569586879528960 |
|---|---|
| author | Gossa Lô Victor de Boer Chris J. van Aart |
| author_facet | Gossa Lô Victor de Boer Chris J. van Aart |
| author_sort | Gossa Lô |
| collection | DOAJ |
| description | This paper examines how machine learning (ML) and natural language processing (NLP) can be used to identify, analyze, and generate West African folk tales. Two corpora of West African and Western European folk tales are compiled and used in three experiments on cross-cultural folk tale analysis. In the text generation experiment, two types of deep learning text generators are built and trained on the West African corpus. We show that although the texts range between semantic and syntactic coherence, each of them contains West African features. The second experiment further examines the distinction between the West African and Western European folk tales by comparing the performance of an LSTM (acc. 0.79) with a BoW classifier (acc. 0.93), indicating that the two corpora can be clearly distinguished in terms of vocabulary. An interactive t-SNE visualization of a hybrid classifier (acc. 0.85) highlights the culture-specific words for both. The third experiment describes an ML analysis of narrative structures. Classifiers trained on parts of folk tales according to the three-act structure are quite capable of distinguishing these parts (acc. 0.78). Common n-grams extracted from these parts not only underline cross-cultural distinctions in narrative structures, but also show the overlap between verbal and written West African narratives. |
| first_indexed | 2024-03-10T20:13:48Z |
| format | Article |
| id | doaj.art-a92c3381fce14c958a98ea82f9580d37 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T20:13:48Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-a92c3381fce14c958a98ea82f9580d372023-11-19T22:44:40ZengMDPI AGInformation2078-24892020-04-0111523610.3390/info11050236Exploring West African Folk Narrative Texts Using Machine LearningGossa Lô0Victor de Boer1Chris J. van Aart2Computer Science Department, Vrije Universiteit Amsterdam, De Boelelaan 1085, 1081 HV Amsterdam, The NetherlandsComputer Science Department, Vrije Universiteit Amsterdam, De Boelelaan 1085, 1081 HV Amsterdam, The NetherlandsBolesian B.V., Hooghiemstraplein 85, 3514 AX Utrecht, The NetherlandsThis paper examines how machine learning (ML) and natural language processing (NLP) can be used to identify, analyze, and generate West African folk tales. Two corpora of West African and Western European folk tales are compiled and used in three experiments on cross-cultural folk tale analysis. In the text generation experiment, two types of deep learning text generators are built and trained on the West African corpus. We show that although the texts range between semantic and syntactic coherence, each of them contains West African features. The second experiment further examines the distinction between the West African and Western European folk tales by comparing the performance of an LSTM (acc. 0.79) with a BoW classifier (acc. 0.93), indicating that the two corpora can be clearly distinguished in terms of vocabulary. An interactive t-SNE visualization of a hybrid classifier (acc. 0.85) highlights the culture-specific words for both. The third experiment describes an ML analysis of narrative structures. Classifiers trained on parts of folk tales according to the three-act structure are quite capable of distinguishing these parts (acc. 0.78). Common n-grams extracted from these parts not only underline cross-cultural distinctions in narrative structures, but also show the overlap between verbal and written West African narratives.https://www.mdpi.com/2078-2489/11/5/236deep learningtext generationtext classificationstorytellingWest Africafolk tales |
| spellingShingle | Gossa Lô Victor de Boer Chris J. van Aart Exploring West African Folk Narrative Texts Using Machine Learning Information deep learning text generation text classification storytelling West Africa folk tales |
| title | Exploring West African Folk Narrative Texts Using Machine Learning |
| title_full | Exploring West African Folk Narrative Texts Using Machine Learning |
| title_fullStr | Exploring West African Folk Narrative Texts Using Machine Learning |
| title_full_unstemmed | Exploring West African Folk Narrative Texts Using Machine Learning |
| title_short | Exploring West African Folk Narrative Texts Using Machine Learning |
| title_sort | exploring west african folk narrative texts using machine learning |
| topic | deep learning text generation text classification storytelling West Africa folk tales |
| url | https://www.mdpi.com/2078-2489/11/5/236 |
| work_keys_str_mv | AT gossalo exploringwestafricanfolknarrativetextsusingmachinelearning AT victordeboer exploringwestafricanfolknarrativetextsusingmachinelearning AT chrisjvanaart exploringwestafricanfolknarrativetextsusingmachinelearning |