id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_fljh2g733fa2fnxmkvwa4p3kby	Noura Al Moubayed	Beyond the topics: how deep learning can improve the discriminability of probabilistic topic modelling	2020	32	.pdf	application/pdf	12754	1537	53	the topics per document into class-dependent deep learning models that extract (SDA) is then used to model the complex relationship among the topics per sentiment Keywords Topic modelling, Stacked denoising autoencoders, Text classification, Sentiment analysis Early work on sentiment analysis approached the problem from the traditional topic-based bag of words for text classification, topic modelling, and sentiment analysis tasks using a Topic modelling is used as a feature extraction method which provides a robust the sentiment of a given text, it is passed through the two topic models and the two SDAs to generate features used by two SDAs for the positive and negative sentiment. (7) between the input data (e.g. topic modelling features) and the reconstructed The topic modelling features of data from both polarities approach compared with the projected topic modelling features on a 2D space using (A) Word sentiment from positive and negative topic models for UMICH.	./cache/work_fljh2g733fa2fnxmkvwa4p3kby.pdf	./txt/work_fljh2g733fa2fnxmkvwa4p3kby.txt