Hybrid Tiled Convolutional Neural Networks (HTCNN) Text Sentiment Classification

Maria Mihaela Truşcǎ*, Gerasimos Spanakis.

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

1 Citation (Web of Science)


The tiled convolutional neural network (TCNN) has been applied only to computer vision for learning invariances. We adjust its architecture to NLP to improve the extraction of the most salient features for sentiment analysis. Knowing that the major drawback of the TCNN in the NLP field is its inflexible filter structure, we propose a novel architecture called hybrid tiled convolutional neural network (HTCNN) that applies a filter only on the words that appear in similar contexts and on their neighbouring words (a necessary step for preventing the loss of some n-grams). The experiments on the IMDB movie reviews dataset demonstrate the effectiveness of the HTCNN that has a higher level of performance of more than 3% and 1% respectively than both the convolutional neural network (CNN) and the TCNN. These results are confirmed by the SemEval-2017 dataset where the recall of the HTCNN model exceeds by more than six percentage points the recall of its simple variant, CNN.

Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Agents and Artificial Intelligence
EditorsAna Rocha, Luc Steels, Jaap van den Herik
Number of pages8
Publication statusPublished - Feb 2020
Event12th International Conference on Agents and Artificial Intelligence - Valetta, Malta
Duration: 22 Feb 202024 Feb 2020


Conference12th International Conference on Agents and Artificial Intelligence
Abbreviated titleICAART 2020
Internet address


  • Hybrid Tiled Convolutional Neural Network
  • Sentiment Analysis

Cite this