Pinned Repositories
BERT-XDD
BERT-XDD is a deep learning methodology for effective and interpretable depression detection from social media posts.
BERT_personality_detection
How to exploit BERT for detecting users' personality type based on some text they have posted, according to the Myers–Briggs Type Indicator (MBTI).
BERT_text_classification
How to fine-tune a BERT classifier for detecting the sentiment of a movie review and the toxicity of a comment.
BLEST-ML
BLEST-ML (BLock size ESTimation through Machine Learning) is a methodology for block size estimation that relies on supervised machine learning techniques.
CNN-VAE-MNIST
This repository is dedicated to the development of a Flask web application capable of drawing digits through the use of a generative model. This model is obtained by training a convolutional variational autoencoder on the MNIST dataset of handwritten digits using Keras+Tensorflow.
DiXtill
DiXtill
H-ADAPTS
H-ADAPTS (Hashtag recommendAtion by Detecting and adAPting to Trend Shifts)
IOM-NN
IOM-NN (Iterative Opinion Mining using Neural Networks) is a software for discovering the polarization of social media users during election campaigns characterized by the competition of political factions. The methodology uses an automatic incremental procedure based on feed-forward neural networks for analyzing the posts published by social media users. Starting from a limited set of classification rules, created from a small subset of hashtags that are notoriously in favor of specific factions, the methodology iteratively generates new classification rules. Such rules are then used to determine the polarization of people towards a faction.
speech_emotion_recognition
How to detect emotions from speech using Bi-directional LSTM networks and attention mechanism in Keras.
TM-FID
TM-FID (Topic-oriented Multimodal False Information Detection)
rcantini's Repositories
rcantini/speech_emotion_recognition
How to detect emotions from speech using Bi-directional LSTM networks and attention mechanism in Keras.
rcantini/BERT_text_classification
How to fine-tune a BERT classifier for detecting the sentiment of a movie review and the toxicity of a comment.
rcantini/BERT_personality_detection
How to exploit BERT for detecting users' personality type based on some text they have posted, according to the Myers–Briggs Type Indicator (MBTI).
rcantini/CNN-VAE-MNIST
This repository is dedicated to the development of a Flask web application capable of drawing digits through the use of a generative model. This model is obtained by training a convolutional variational autoencoder on the MNIST dataset of handwritten digits using Keras+Tensorflow.
rcantini/HASHET
HASHET (HAshtag recommendation using Sentence-to-Hashtag Embedding Translation), is a neural model aimed at suggesting a relevant set of hashtags for a given post. It exploits the most recent NLP techniques and is based on two independent latent spaces for embedding the text of a post and the hashtags it contains. A mapping process based on a multilayer perceptron is then used for learning a translation from the semantic features of the text to the latent representation of its hashtags.
rcantini/BERT-XDD
BERT-XDD is a deep learning methodology for effective and interpretable depression detection from social media posts.
rcantini/BLEST-ML
BLEST-ML (BLock size ESTimation through Machine Learning) is a methodology for block size estimation that relies on supervised machine learning techniques.
rcantini/DiXtill
DiXtill
rcantini/Dog-breed-classification
How to build a dog breed classifier with Keras and Tensorflow using Convolutional Neural Networks. The model is based on the VGG16 architecture and exploits transfer learning and fine tuning techniques.
rcantini/H-ADAPTS
H-ADAPTS (Hashtag recommendAtion by Detecting and adAPting to Trend Shifts)
rcantini/IOM-NN
IOM-NN (Iterative Opinion Mining using Neural Networks) is a software for discovering the polarization of social media users during election campaigns characterized by the competition of political factions. The methodology uses an automatic incremental procedure based on feed-forward neural networks for analyzing the posts published by social media users. Starting from a limited set of classification rules, created from a small subset of hashtags that are notoriously in favor of specific factions, the methodology iteratively generates new classification rules. Such rules are then used to determine the polarization of people towards a faction.
rcantini/TM-FID
TM-FID (Topic-oriented Multimodal False Information Detection)
rcantini/IIWM
Intelligent In-memory Workflow Manager is a machine learning solution for optimizing the in-memory execution of data-intensive workflows on parallel machines. This repository offers the dataset used to train the performance estimation model employed by IIWM to guide task scheduling, which relies on a heuristic solution to the bin packing problem.
rcantini/LLM-Bias-Jailbreak
Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation
rcantini/rcantini.github.io
My academic website