@unpublished{Nassourou2011,
  author    = {Nassourou, Mohamadou},
  title     = {A Rule-based Statistical Classifier for Determining a Base Text and Ranking Witnesses In Textual Documents Collation Process},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-57465},
  year      = {2011},
  abstract  = {Given a collection of diverging documents about some lost original text, any person interested in the text would try reconstructing it from the diverging documents. Whether it is eclecticism, stemmatics, or copy-text, one is expected to explicitly or indirectly select one of the documents as a starting point or as a base text, which could be emended through comparison with remaining documents, so that a text that could be designated as the original document is generated. Unfortunately the process of giving priority to one of the documents also known as witnesses is a subjective approach. In fact even Cladistics, which could be considered as a computer-based approach of implementing stemmatics, does not present or recommend users to select a certain witness as a starting point for the process of reconstructing the original document. In this study, a computational method using a rule-based Bayesian classifier is used, to assist text scholars in their attempts of reconstructing a non-existing document from some available witnesses. The method developed in this study consists of selecting a base text successively and collating it with remaining documents. Each completed collation cycle stores the selected base text and its closest witness, along with a weighted score of their similarities and differences. At the end of the collation process, a witness selected more often by majority of base texts is considered as the probable base text of the collection. Witnesses' scores are weighted using a weighting system, based on effects of types of textual modifications on the process of reconstructing original documents. Users have the possibility to select between baseless and base text collation. If a base text is selected, the task is reduced to ranking the witnesses with respect to the base text, otherwise a base text as well as ranking of the witnesses with respect to the base text are computed and displayed on a histogram.},
  subject      = {Textvergleich},
  language  = {en}
}
@unpublished{Nassourou2011,
  author    = {Nassourou, Mohamadou},
  title     = {A Knowledge-based Hybrid Statistical Classifier for Reconstructing the Chronology of the Quran},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-54712},
  year      = {2011},
  abstract  = {Computationally categorizing Quran's chapters has been mainly confined to the determination of chapters' revelation places. However this broad classification is not sufficient to effectively and thoroughly understand and interpret the Quran. The chronology of revelation would not only improve comprehending the philosophy of Islam, but also the easiness of implementing and memorizing its laws and recommendations. This paper attempts estimating possible chapters' dates of revelation through their lexical frequency profiles. A hybrid statistical classifier consisting of stemming and clustering algorithms for comparing lexical frequency profiles of chapters, and deriving dates of revelation has been developed. The classifier is trained using some chapters with known dates of revelation. Then it classifies chapters with uncertain dates of revelation by computing their proximity to the training ones. The results reported here indicate that the proposed methodology yields usable results in estimating dates of revelation of the Quran's chapters based on their lexical contents.},
  subject      = {Text Mining},
  language  = {en}
}
@unpublished{Nassourou2011,
  author    = {Nassourou, Mohamadou},
  title     = {Computer-based Textual Documents Collation System for Reconstructing the Original Text from Automatically Identified Base Text and Ranked Witnesses},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-65749},
  year      = {2011},
  abstract  = {Given a collection of diverging documents about some lost original text, any person interested in the text would try reconstructing it from the diverging documents. Whether it is eclecticism, stemmatics, or copy-text, one is expected to explicitly or indirectly select one of the documents as a starting point or as a base text, which could be emended through comparison with remaining documents, so that a text that could be designated as the original document is generated. Unfortunately the process of giving priority to one of the documents also known as witnesses is a subjective approach. In fact even Cladistics, which could be considered as a computer-based approach of implementing stemmatics, does not present or recommend users to select a certain witness as a starting point for the process of reconstructing the original document. In this study, a computational method using a rule-based Bayesian classifier is used, to assist text scholars in their attempts of reconstructing a non-existing document from some available witnesses. The method developed in this study consists of selecting a base text successively and collating it with remaining documents. Each completed collation cycle stores the selected base text and its closest witness, along with a weighted score of their similarities and differences. At the end of the collation process, a witness selected more often by majority of base texts is considered as the probable base text of the collection. Witnesses' scores are weighted using a weighting system, based on effects of types of textual modifications on the process of reconstructing original documents. Users have the possibility to select between baseless and base text collation. If a base text is selected, the task is reduced to ranking the witnesses with respect to the base text, otherwise a base text as well as ranking of the witnesses with respect to the base text are computed and displayed on a bar diagram. Additionally this study includes a recursive algorithm for automatically reconstructing the original text from the identified base text and ranked witnesses.},
  subject      = {Textvergleich},
  language  = {en}
}