An Automated News Bias Classifier Using Caenorhabditis Elegans Inspired
Recursive Feedback Network Architecture
- URL: http://arxiv.org/abs/2207.12724v1
- Date: Tue, 26 Jul 2022 08:26:26 GMT
- Title: An Automated News Bias Classifier Using Caenorhabditis Elegans Inspired
Recursive Feedback Network Architecture
- Authors: Agastya Sridharan and Natarajan S
- Abstract summary: We propose a network architecture that achieves human-level accuracy in assigning bias classifications to articles.
The model is trained on over ten-thousand articles scraped from AllSides.com which are labelled to indicate political bias.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Traditional approaches to classify the political bias of news articles have
failed to generate accurate, generalizable results. Existing networks premised
on CNNs and DNNs lack a model to identify and extrapolate subtle indicators of
bias like word choice, context, and presentation. In this paper, we propose a
network architecture that achieves human-level accuracy in assigning bias
classifications to articles. The underlying model is based on a novel Mesh
Neural Network (MNN),this structure enables feedback and feedforward synaptic
connections between any two neurons in the mesh. The MNN ontains six network
configurations that utilize Bernoulli based random sampling, pre-trained DNNs,
and a network modelled after the C. Elegans nematode. The model is trained on
over ten-thousand articles scraped from AllSides.com which are labelled to
indicate political bias. The parameters of the network are then evolved using a
genetic algorithm suited to the feedback neural structure. Finally, the best
performing model is applied to five popular news sources in the United States
over a fifty-day trial to quantify political biases in the articles they
display. We hope our project can spur research into biological solutions for
NLP tasks and provide accurate tools for citizens to understand subtle biases
in the articles they consume.
Related papers
- Convolutional Neural Networks for Sentiment Analysis on Weibo Data: A
Natural Language Processing Approach [0.228438857884398]
This study addresses the complex task of sentiment analysis on a dataset of 119,988 original tweets from Weibo using a Convolutional Neural Network (CNN)
A CNN-based model was utilized, leveraging word embeddings for feature extraction, and trained to perform sentiment classification.
The model achieved a macro-average F1-score of approximately 0.73 on the test set, showing balanced performance across positive, neutral, and negative sentiments.
arXiv Detail & Related papers (2023-07-13T03:02:56Z) - How neural networks learn to classify chaotic time series [77.34726150561087]
We study the inner workings of neural networks trained to classify regular-versus-chaotic time series.
We find that the relation between input periodicity and activation periodicity is key for the performance of LKCNN models.
arXiv Detail & Related papers (2023-06-04T08:53:27Z) - Neural Additive Models for Location Scale and Shape: A Framework for
Interpretable Neural Regression Beyond the Mean [1.0923877073891446]
Deep neural networks (DNNs) have proven to be highly effective in a variety of tasks.
Despite this success, the inner workings of DNNs are often not transparent.
This lack of interpretability has led to increased research on inherently interpretable neural networks.
arXiv Detail & Related papers (2023-01-27T17:06:13Z) - Visualising and Explaining Deep Learning Models for Speech Quality
Prediction [0.0]
The non-intrusive speech quality prediction model NISQA is analyzed in this paper.
It is composed of a convolutional neural network (CNN) and a recurrent neural network (RNN)
arXiv Detail & Related papers (2021-12-12T12:50:03Z) - Towards Measuring Bias in Image Classification [61.802949761385]
Convolutional Neural Networks (CNN) have become state-of-the-art for the main computer vision tasks.
However, due to the complex structure their decisions are hard to understand which limits their use in some context of the industrial world.
We present a systematic approach to uncover data bias by means of attribution maps.
arXiv Detail & Related papers (2021-07-01T10:50:39Z) - BreakingBED -- Breaking Binary and Efficient Deep Neural Networks by
Adversarial Attacks [65.2021953284622]
We study robustness of CNNs against white-box and black-box adversarial attacks.
Results are shown for distilled CNNs, agent-based state-of-the-art pruned models, and binarized neural networks.
arXiv Detail & Related papers (2021-03-14T20:43:19Z) - Informative Dropout for Robust Representation Learning: A Shape-bias
Perspective [84.30946377024297]
We propose a light-weight model-agnostic method, namely Informative Dropout (InfoDrop), to improve interpretability and reduce texture bias.
Specifically, we discriminate texture from shape based on local self-information in an image, and adopt a Dropout-like algorithm to decorrelate the model output from the local texture.
arXiv Detail & Related papers (2020-08-10T16:52:24Z) - Neural Networks with Recurrent Generative Feedback [61.90658210112138]
We instantiate this design on convolutional neural networks (CNNs)
In the experiments, CNN-F shows considerably improved adversarial robustness over conventional feedforward CNNs on standard benchmarks.
arXiv Detail & Related papers (2020-07-17T19:32:48Z) - Learning from Failure: Training Debiased Classifier from Biased
Classifier [76.52804102765931]
We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge.
We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously.
Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
arXiv Detail & Related papers (2020-07-06T07:20:29Z) - The shape and simplicity biases of adversarially robust ImageNet-trained
CNNs [9.707679445925516]
We study the shape bias and internal mechanisms that enable the generalizability of AlexNet, GoogLeNet, and ResNet-50 models trained via adversarial training.
Remarkably, adversarial training induces three simplicity biases into hidden neurons in the process of "robustifying" CNNs.
arXiv Detail & Related papers (2020-06-16T16:38:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.