Parlar, Soyhan
Email Address
Birth Date
Search results
Naïve Bayes and named entity recognition for requirements mining in job postings
2021, Wild, Simon, Parlar, Soyhan, Hanne, Thomas, Dornberger, Rolf
This paper analyses how the required skills in a job post can be extracted. With an automated extraction of skills from unstructured text, applicants could be more accurately matched and search engines could provide better recommendations. The problem is optimized by classifying the relevant parts of the description with a multinomial naïve Bayes model. The model identifies the section of the unstructured text in which the requirements are stated. Subsequently, a named entity recognition (NER) model extracts the required skills from the classified text. This approach minimizes the false positives since the data which is analyzed is already filtered. The results show that the naïve Bayes model classifies up to 99% of the sections correctly, and the NER model extracts 65% of the skills required for a position. The accuracy of the NER model is not sufficient to be used in production. On the validation set, the performance was insufficient. A more consistent labelling guideline would be needed and more data should be annotated to increase the performance.
Case model for the RoboInnoCase recommender system for cases of digital business transformation: structuring information for a case of digital change
2019, Witschel, Hans Friedrich, Peter, Marco, Seiler, Laura, Parlar, Soyhan, Gatziu Grivas, Stella, Bernardino, Jorge, Salgado, Ana, Filipe, Joaquim
In this work, we develop a case model to structure cases of past digital transformations which act as input data for a recommender system. The purpose of that recommender is to act as an inspiration and support for new cases of digital transformation. To define the case model, case analyses, where 40 cases of past digital transformations are analysed and coded to determine relevant attributes and values, literature research and the particularities of the case for digital change, are used as a basis. The case model is evaluated by means of an experiment where two different scenarios are fed into a prototypical case-based recommender system and then matched, based on an entropically derived weighting system, with the case base that contains cases structured according to the case model. The results not only suggest that the case model’s functionality can be guaranteed, but that a good quality of the given recommendations is achieved by applying a case-based recommender system using the proposed case model. The results not only suggest that the case model’s functionality can be guaranteed, but that a good quality of the given recommendations is achieved by applying a case-based recommender system using the proposed case model.