This course provides students with a practical knowledge of text analysis techniques and Natural Language Processing. The focus of the module will be on how these techniques are used in the analysis of large data sets. This module is to be offered on the Master of Engineering in Electronic & Computer Engineering Pre-requisite for this module is module ID 3301

The course will cover the following aspects: 1. Fundamentals: students will be introduced to basic concepts of text analytics, such as application domains, tasks, NLP aspects of text analysis, text pre-processing (tokenization, stemming, stop-word removal), text representation and modelling (Ngrams, bag of words, bag of concepts, word embedding), benchmarking and evaluation methods (standard datasets, precision, recall, F-measure, ROC curve). 2. Tasks & Tools: Consideration of the main text analytics tasks and techniques such as, text categorization, text clustering, concept/entity extraction, sentiment analysis, text summarization, and language detection. In this part students will practice with some of the popular open-source tools that implement text analytics tasks (e.g., RapidMiner, Weka, Carrot2, LingPipe, NLTK, Ontotext, GATE). 3. Big Data & Cloud: Students will gain a practical knowledge of big data text analytics by learning to conduct text analytics experiments and pipelines in commercially available cloud platforms. Students will also gain practice in the use of well known chaining text analytics cloud APIs such as: IBM Watson's Natural Language Understanding, Google Cloud Natural Language, Amazon Comprehend, and Microsoft Azure Text Analytics API. 4. Emerging trends in text analytics and NLP. The practical experiments and platforms that are considered in this module will reflect the current state of the art in Text Analytics and NLP.

At the end of this module the students will be able to (i) Process a simple text stream using industry standard analysis tools. (ii) Classify and extract features from a data stream (iii) Perform sentiment analysis on a data stream (iv) Use open source tools for text and data analytics.

N/A

The students will develop the ability to use practical open source tools for text and data analytics.

The module will be taught using a conventional mix of lectures and laboratories. Recent developments in the area of blended learning will be exploited to facilitate the efficient delivery of the material. The module builds on research output from the relevant ECE research group in the this space, TAKO @UL