Advanced NLP and Machine Learning for text analysi
NOTES: Participants are required to attend the following workshops or have working knowledge of Python and Machine Learning models:
* Introduction to Python and Data Analytics in Python
* Collecting and analysing social media data using Python
* Introduction to Natural Language Processing in Python
A subfield of Artificial Intelligence, Machine Learning (ML) is the process of enabling computers to learn on their own without being explicitly programmed by identifying patterns or structures within input data, building models and predicting future behaviours. From product recommendation (marketing and sales) to fraud detection (financial services), applications of Machine Learning can be seen in various fields today. Most NLP tasks are often performed using different Machine Learning algorithms ranging from classification models (supervised learning) for Sentiment Analysis and Named Entity Classification to clustering (unsupervised learning) for tasks such as Outlier Detection.
A detailed overview of various ML algorithms used to perform Sentiment Analysis shall be presented in this workshop. A case study of visitor reviews of Exeter Cathedral collected from TripAdvisor shall be analysed to predict visitor sentiment for various aspects identified within the data. This case study is currently being conducted in the VISTA AR project – a project aimed at developing an understanding of visitor experiences by using Text Analytics (among other approaches) to analyse visitor feedback collected from cultural heritage locations.
Dr. Pikakshi Manchanda
Postdoctoral Research Fellow, VISTA AR
University of Exeter Business School
Pikakshi holds a Ph.D. in Natural Language Processing (Text Analytics) from University of Milano-Bicocca, Milan, Italy. Currently she is working as a Postdoctoral Research Fellow within the VISTA AR project. Her research had been an effort towards ‘Adaptation of Named Entity Recognition and Linking Framework’ for social media streams and different ontologies that come along with the task. Before doing her PhD, she obtained her Masters in Information Technology from YMCA University of Science and Technology, India and, thereafter, worked with IBM India for over a year. Her research interests include Text Analytics, Information Extraction, Social Media Analysis, Knowledge Discovery and Semantic Web Technologies.