Editorial

Abstract

This issue of the Polytechnic Open Library International Bulletin of Information Technology and Science (POLIBITS) includes ten papers by authors from India, Germany, Tunisia, Italy and Algeria. The majority of the papers included in this issue are devoted to the general topic of emerging challenges and trends in business intelligence, including such specific topics as software development, pattern recognition, natural language processing, forecasting, Internet of things, time series analysis, as well as optimization and multi-objective optimization.

Pruthwik Mishra et al. in their paper Arithmetic Word Problem Solver Using Frame Identification”, The paper presents a novel approach for automatic arithmetic word problem solving using frame identification. Overall, the paper presents a promising approach for automatic arithmetic word problem solving, with room for improvement and future research directions.

Wael Alkhatib, et al. in their paper “Comparison of Feature Selection Techniques for Multi-label Text Classification against a New Semantic-based Method”, presents a comparative study of various feature selection techniques for multi-label text classification, with a focus on incorporating text semantics into feature selection, the paper provides valuable insights into the importance of feature selection techniques, particularly in the context of multi-label text classification, and demonstrates the effectiveness of incorporating text semantics for improved classification performance.

Khaireddine Bacha, in his paper Design and Realization of an Environment of CALL for the Teaching of the Arabic Language” explores the intersection of Natural Language Processing (NLP) and Computer Assisted Language Learning (CALL) for the teaching of Arabic. The paper emphasizes the integration of NLP techniques into CALL systems to enhance the teaching and learning of the Arabic language, addressing challenges and proposing solutions for creating effective learning environments.

Giovanni Siragusa, in his paper “A Neural Topic Summarizer: using Topic Model to Enrich Abstractive Summaries” resents a model called NeTSumm that combines neural networks with topics extracted on-the-fly to improve abstractive summarization. While existing neural models for summarization focus on the encoder-decoder framework, NeTSumm integrates topics to capture thematic structures in the input text, aiming to enhance the quality of generated summaries.

Djaidri Asma et al. in their paper “A New Arabic Word Embeddings model for Word Sense Induction” describes a new approach to Arabic word sense induction using word embeddings.by the plants' roots, the paper introduces a novel method for Arabic word sense induction, leveraging word embeddings and graph clustering techniques, with promising results.

This issue of the journal will be useful to researchers, students, and practitioners working in the corresponding areas, as well as to public in general interested in advances in computer science, artificial intelligence, and computer engineering.

Guest Editors