Tutorials
The role of the tutorials is to provide a platform for a more intensive scientific exchange amongst researchers interested in a particular topic and as a meeting point for the community. Tutorials complement the depth-oriented technical sessions by providing participants with broad overviews of emerging fields. A tutorial can be scheduled for 1.5 or 3 hours.
TUTORIALS LIST
Sentiment Analysis on Social Media (ICETE)
Instructor : Alessandro Ortis
Sentiment Analysis on
Social Media
Instructor
|
Alessandro Ortis
University of Catania, Department of Mathematics and Computer Science
Italy
|
|
|
|
Brief Bio
Alessandro Ortis is a post-doc researcher at the University of Catania. He has been working in the field of Computer Vision research since 2012, when he joined to the IPLab (Image Processing Laboratory). In 2015 Alessandro was awarded with the Archimede Prize for the excellence of academic career conferred by the University of Catania. In January 2019 he has achieved the PhD in Mathematics and Computer Science, with a PhD Thesis entitled “Methods for Sentiment Analysis and Social Media Popularity of Crowdsourced Visual Contents”. The thesis investigates several aspects related to Visual Sentiment Analysis, applied on crowdsourced images and videos. His PhD has been granted by TIM – Telecom Italia. The main goal of the presented works is to infer the users' preferences by exploiting the crowdsourcing paradigm, as well as to predict the impact of visual contents shared through social media networks. Alessandro spent a part of his PhD as a Visiting Researcher at the Imperial College in London, during which he addressed problems related to the assessment of social influencer advertising campaigns performed through social media. His research interests lie in the fields of Computer Vision, Machine Learning and Multimedia.
|
Abstract
Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to all human activities and are key influencers of our behaviours. In the context of social media, uploading text messages, images and videos to a social network platform is the new way by which people share their opinions and experiences. Such huge amount of heterogeneous information produced directly by users is publicly available and can be analysed by proper techniques. In this tutorial, an overview of the field will be presented considering either scientific works and practical methods. Then, the main techniques to perform sentiment analysis on text and images will be presented.
Keywords
Sentiment Analysis, Social Media, NLP, Visual Sentiment Analysis, Multimedia
Aims and Learning Objectives
The aim of this tutorial is to provide a complete overview of the sentiment analysis field, applied on both texts and images coming from social platform. For each technique and concept, practical code examples will be presented. The final goal is to provide the main available tools in terms of techniques and related code libraries, with a knowledge of the scientific background.
Target Audience
The tutorial is intended for both experts who are interested in having a broader overview in sentiment analysis on contents published on social media platforms, with practical examples. The tutorial will include also an introduction of the field, with connections between context, tasks and techniques. Therefore, also not experts will benefit from the tutorial.
Prerequisite Knowledge of Audience
Basic statistics, basic Python knowledge.
Detailed Outline
I) Social media platforms (APIs):
- concept and examples
- main social networks’ APIs
- crawling posts from Flickr
II) Textual sentiment analysis:
- Aims and motivations
- Natural Language Processing
- BoW
- TF-IDF
- word2vec
- doc2vec
III) Image sentiment analysis:
- Introduction
- state of the art
- challenges
- image polarity prediction
- image popularity prediction
- image virality