The impact and dynamics of Internet-based resources for Arabic-speaking users is increasing in significance, depth and breadth at highest pace than ever, and thus requires updated mechanisms for computational processing of Arabic texts. Arabic is a complex language and as such requires in depth investigation for analysis and improvement of available automatic processing techniques such as root extraction methods or text classification techniques, and for developing text collections that are already labeled, whether with single or multiple labels. This thesis proposes new ideas and methods to improve available automatic processing techniques for Arabic texts. Any automatic processing technique would require data in order to be used and critically reviewed and assessed, and here an attempt to develop a labeled Arabic corpus is also proposed. This thesis is composed of three parts: 1- Arabic corpus development, 2- proposing, improving and implementing root extraction techniques, and 3- proposing and investigating the effect of different pre-processing methods on single-labeled text classification methods for Arabic. This thesis first develops an Arabic corpus that is prepared to be used here for testing root extraction methods as well as single-label text classification techniques. It also enhances a rule-based root extraction method by handling irregular cases (that appear in about 34% of texts). It proposes and implements two expanded algorithms as well as an adjustment for a weight-based method. It also includes the algorithm that handles irregular cases to all and compares the performances of these proposed methods with original ones. This thesis thus develops a root extraction system that handles foreign Arabized words by constructing a list of about 7,000 foreign words. The outcome of the technique with best accuracy results in extracting the correct stem and root for respective words in texts, which is an enhanced rule-based method, is used in the third part of this thesis. This thesis finally proposes and implements a variant term frequency inverse document frequency weighting method, and investigates the effect of using different choices of features in document representation on single-label text classification performance (words, stems or roots as well as including to these choices their respective phrases). This thesis applies forty seven classifiers on all proposed representations and compares their performances. One challenge for researchers in Arabic text processing is that reported root extraction techniques in literature are either not accessible or require a long time to be reproduced while labeled benchmark Arabic text corpus is not fully available online. Also, by now few machine learning techniques were investigated on Arabic where usual preprocessing steps before classification were chosen. Such challenges are addressed in this thesis by developing a new labeled Arabic text corpus for extended applications of computational techniques. Results of investigated issues here show that proposing and implementing an algorithm that handles irregular words in Arabic did improve the performance of all implemented root extraction techniques. The performance of the algorithm that handles such irregular cases is evaluated in terms of accuracy improvement and execution time. Its efficiency is investigated with different document lengths and empirically is found to be linear in time for document lengths less than about 8,000. The rule-based technique is improved the highest among implemented root extraction methods when including the irregular cases handling algorithm. This thesis validates that choosing roots or stems instead of words in documents representations indeed improves single-label classification performance significantly for most used classifiers. However, the effect of extending such representations with their respective phrases on single-label text classification performance shows that it has no significant improvement. Many classifiers were not yet tested for Arabic such as the ripple-down rule classifier. The outcome of comparing the classifiers' performances concludes that the Bayesian network classifier performance is significantly the best in terms of accuracy, training time, and root mean square error values for all proposed and implemented representations. / Petra University, Amman (Jordan)

<p>Glavni cilj ove doktorske disertacije je određivanje hemijskog sastava, biolo&scaron;kih i funkcionalnih karakteristika novih proizvoda od zove. Dobijanje proizvoda na bazi zove zasniva se na primeni tradicionalnih i savremenih tehnolo&scaron;kih procesa proizvodnje. Iskori&scaron;ćenje prirodnog potencijala zove započeto je primenom tradicionalne i savremene (liofilizacija) tehnike su&scaron;enja. U cilju dobijanja visoko-vrednih ekstrakata ploda i cveta zove primenjene su tradicionalna (maceracija) i savremene (ultrazvučna i mikrotalasna) ekstrakcione tehnike sa dva ekstragensa (50% etanol i voda). Dobijanje matičnog soka od plodova zove podrazumevalo je primenu tradicionalnog načina ceđenja, dok je vino od plodova zove dobijeno po standardnom postupku proizvodnje vina. Vino je izloženo različitim temperaturnim tretmanima u različitom vremenskom periodu (60 &deg;C u toku 5 minuta, 60 &deg;C u toku 10 minuta, 70 &deg;C u toku 5 minuta i bez toplotnog tretmana) u cilju evaluacije biolo&scaron;ke aktivnosti dobijenog proizvoda. Etarsko ulje ploda i cveta zove je dobijeno hidrodestilacijom. Ispitivanje efikasnosti primenjenih tehnolo&scaron;kih postupaka su&scaron;enja i ekstrakcije je zasnovano na određivanju biolo&scaron;kih i funkcionalnih karakteristika dobijenih ekstrakata ploda i cveta zove. U ispitivanim ekstraktima ploda i cveta zove dominantne fenolne kiseline su hlorogenska i protokatehinska kiselina, a rutin i kvercetin-3-O-heksozid su dominantna flavonoidna jedinjenja. Biolo&scaron;ke i funkcionalne karakteristike su ispitane primenom različitih in vitro antioksidativnih, neuroprotektivnih, antitirozinaznih i antidijabetogenih testova. Primenom liofilizacije kao savremene tehnike su&scaron;enja i mikrotalasne ekstrakcije kao savremene ekstrakcione tehnike povećava se biopotencijal ispitivanih ekstrakata. Matični sok od plodova zove kao potencijalno novi funkcionalni proizvod je analiziran u cilju definisanja hemijskog, fitohemijskog i nutritivnog sastava, biolo&scaron;kog potencijala i senzorskih karakteristika. Ispitivanja dobijenog vina su bila usmerena na utvrđivanje optimalnih uslova za proizvodnju voćnog vina. Definisanjem hemijskog i fitohemijskog sastava i evaluacijom biopotencijala vina određen je optimalan temperaturni profil za dobijanje jednog od novih funkcionalnih proizvoda. Na osnovu utvrđenog hemijskog sastava etarsko ulje ploda i cveta zove se pokazalo kao potencijalno novi prirodni agens za održavanje svežine i produženja roka trajanja prehrambenih proizvoda. Zova je nesumnjivo samonikla biljna vrsta koja u budućnosti osnovano može biti polazna sirovina za kreiranje i dobijanje novih prehrmabenih proizvoda na domaćem i inostranom trži&scaron;tu.</p> / <p>The main goal of this doctoral dissertation is to determine the chemical composition, biological and functional characteristics of new elderberry products. Elderberry products were obtained via traditional and modern technological processes. The exploitation of the natural potential of the elderberry started with the application of traditional and modern (lyophilization) drying techniques. To obtain high-value extracts of fruits and flowers, traditional (maceration) and modern (ultrasonic and microwave) extraction techniques with two solvents (50% ethanol and water) were applied. Obtaining the juice from the elderberry fruits implied the application of the traditional cold pressing method, whereas wine from the elderberry fruits was obtained in accordance with the standard procedure of wine production. The wine was exposed to different temperature treatments in different periods (60&deg;C for 5 minutes, 60&deg;C for 10 minutes, 70&deg;C for 5 minutes and without heat treatment) to evaluate the biological activity of the product. The essential oil of the fruit and flower was obtained by hydrodistillation. The examination of the efficiency of the applied technological procedures of drying and extraction is based on observing the biological and functional characteristics of the obtained extracts of the said fruits and flowers. In the examined fruit and flower extracts, the dominant phenolic acids are chlorogenic and protocatechuic acid, while rutin and quercetin-3-O-hexoside are the dominant flavonoid compounds. Biological and functional characteristics were examined using various in vitro antioxidant, neuroprotective, antityrosinase, and antidiabetic tests. The application of lyophilization and microwave extraction (as modern drying and extraction techniques) increased the biopotential of the analyzed extracts. Elderberry juice, a potentially new functional product, was analyzed to define the chemical, phytochemical and nutritional composition, biological potential, and sensory characteristics. The wine was tested in order to determine the optimal conditions for the production of fruit wine. By defining the chemical and phytochemical composition and evaluating the biopotential of wine, the optimal temperature profile for obtaining one of the new functional products was determined. Based on the obtained chemical composition, it is determined that the essential oil of fruits and flowers is a potentially new natural agent for maintaining freshness and extending the shelf life of food products. Without a doubt, elderberry is a wild plant species that could be used in the future as the starting material for creating and obtaining new food products on the domestic and foreign markets.</p>