# Reducing Computational Costs in Sentiment Analysis: Tensorized Recurrent Networks vs. Recurrent Networks

arXiv: https://arxiv.org/abs/2306.09705 · HTML: https://mlsanity.com/paper/2306.09705/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 16 Jun 2023.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [A Survey of Transformers](https://mlsanity.com/paper/2106.04554/) (2021)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [The COVID-19 Social Media Infodemic](https://mlsanity.com/paper/2003.05004/) (2020)
- [Tensor-Train Recurrent Neural Networks for Video Classification](https://mlsanity.com/paper/1707.01786/) (2017)
- [Exploiting BERT for End-to-End Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1910.00883/) (2019)
- [An Efficient Procedure for Mining Egocentric Temporal Motifs](https://mlsanity.com/paper/2110.01391/) (2021)
- [Help! Need Advice on Identifying Advice](https://mlsanity.com/paper/2010.02494/) (2020)
- [Modeling International Mobility using Roaming Cell Phone Traces during COVID-19 Pandemic](https://mlsanity.com/paper/2201.02470/) (2022)
- [TEP-GNN: Accurate Execution Time Prediction of Functional Tests using Graph Neural Networks](https://mlsanity.com/paper/2208.11947/) (2022)
- [Leveraging Mobile Phone Data for Migration Flows](https://mlsanity.com/paper/2105.14956/) (2021)
- [A Unified Active Learning Framework for Annotating Graph Data with Application to Software Source Code Performance Prediction](https://mlsanity.com/paper/2304.13032/) (2023)
- [Understanding Human Mobility from Twitter](https://mlsanity.com/paper/1412.2154/) (2014)
- [Emotion Analysis using Multi-Layered Networks for Graphical Representation of Tweets](https://mlsanity.com/paper/2207.00907/) (2022)
- [Criminal Networks Analysis in Missing Data scenarios through Graph Distances](https://mlsanity.com/paper/2103.00457/) (2021)
- [Predicting human mobility through the assimilation of social media traces into mobility models](https://mlsanity.com/paper/1601.04560/) (2016)
- [Impact of the Covid 19 outbreaks on the italian twitter vaccination debat: a network based analysis](https://mlsanity.com/paper/2306.02838/) (2023)

## Abstract (arXiv)

Anticipating audience reaction towards a certain text is integral to several facets of society ranging from politics, research, and commercial industries. Sentiment analysis (SA) is a useful natural language processing (NLP) technique that utilizes lexical/statistical and deep learning methods to determine whether different-sized texts exhibit positive, negative, or neutral emotions. Recurrent networks are widely used in machine-learning communities for problems with sequential data. However, a drawback of models based on Long-Short Term Memory networks and Gated Recurrent Units is the significantly high number of parameters, and thus, such models are computationally expensive. This drawback is even more significant when the available data are limited. Also, such models require significant over-parameterization and regularization to achieve optimal performance. Tensorized models represent a potential solution. In this paper, we classify the sentiment of some social media posts. We compare traditional recurrent models with their tensorized version, and we show that with the tensorized models, we reach comparable performances with respect to the traditional models while using fewer resources for the training.