This lecture will cover the basic concepts of Artificial Neural Networks (ANNs): Biological neural models, Perceptron, Activation functions, Loss types, Steepest Gradient Descent, On-line Perceptron training, Batch Perceptron training.
Archives: Resources
Resource description
e-Symposium 2023: A methodology for Forecasting Election results from Tweets
Social networks as the virtual equivalent of the ancient agora have become a preeminent space of political discourse. They can nurture new political trends and reveal existing ones. Acting as public opinion logs they provide an insight to the evolution of political views and thus have the potential to become proxies of future election results.… Continue reading e-Symposium 2023: A methodology for Forecasting Election results from Tweets
e-Symposium 2023: Political barometer: public opinion mining using tweets
Since the formulation of states, political authorities and political parties have sought to gauge public opinion. In recent years, opinion polls have been able to gratify this need rather efficiently. However, they are expensive to run, and their results may be biased primarily due to improper population sampling. As social networks are used on political… Continue reading e-Symposium 2023: Political barometer: public opinion mining using tweets
e-Symposium 2023: Tweet sentiment analysis
Sentiment analysis in texts, also known as opinion mining, is a significant Natural Language Processing (NLP) task, with many applications in automated social media monitoring, customer feedback processing, e-mail scanning, etc. Sentiments like polarity, aggression, and bias can be recognised in tweets. Typically, such methods combine word embedding approaches and NN sentiment recognition layers. This… Continue reading e-Symposium 2023: Tweet sentiment analysis
e-Symposium 2023: Natural Language processing for political text analysis
Natural Language Processing (NLP) is a subfield of artificial intelligence and computational linguistics with the goal of “understanding” human language. Although its roots can be traced back to the 1950’s, the combination of increased computational power, novel deep learning algorithms and the availability of big corpora has brought about a revolution in the field. Large… Continue reading e-Symposium 2023: Natural Language processing for political text analysis
e-Symposium 2023: Analysing arguments from political debates: obtained results and open challenges
Argumentation in political context has been studied since antiquity, and it still raises a continuous inquiry given the challenging topic. As underlined by Aristotle, rhetorical argumentation is closely associated with ethics and politics, and, whilst in principle contextindependent, “argument analysis is particularly pertinent to forms of argumentation in public contexts’’. These argumentation studies applied to… Continue reading e-Symposium 2023: Analysing arguments from political debates: obtained results and open challenges