Topological data analysis for fake news detection
This project aims to contribute to the under-researched field of topological data analysis (TDA) for text classification through the task of fake news detection. For this task, three individual models have been used: least absolute shrinkage and selection operator (LASSO) using 0th Dimensional Persi...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/156821 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-156821 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1568212023-02-28T23:19:28Z Topological data analysis for fake news detection Deng, Ran Fedor Duzhin School of Physical and Mathematical Sciences FDuzhin@ntu.edu.sg Science::Mathematics::Topology Science::Mathematics::Statistics This project aims to contribute to the under-researched field of topological data analysis (TDA) for text classification through the task of fake news detection. For this task, three individual models have been used: least absolute shrinkage and selection operator (LASSO) using 0th Dimensional Persistent Image (PI) vectors, Bidirectional Long Short-Term Memory (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). Two ensemble models were also used to improve performances by supplementing contextual information from deep-learning models with structural information from PI vectors: BiLSTM + TDA and BERT + TDA. The results suggest that when structural information is given equal or lesser influence than contextual information, the ensemble performs better than the base models on average. This project offers a possible way of utilising TDA features to improve performances in text classification tasks, and a comparison between different models for organizations concerned with false information detection in general. Bachelor of Science in Mathematical Sciences 2022-04-26T07:17:10Z 2022-04-26T07:17:10Z 2022 Final Year Project (FYP) Deng, R. (2022). Topological data analysis for fake news detection. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/156821 https://hdl.handle.net/10356/156821 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Science::Mathematics::Topology Science::Mathematics::Statistics |
spellingShingle |
Science::Mathematics::Topology Science::Mathematics::Statistics Deng, Ran Topological data analysis for fake news detection |
description |
This project aims to contribute to the under-researched field of topological data analysis (TDA) for text classification through the task of fake news detection. For this task, three individual models have been used: least absolute shrinkage and selection operator (LASSO) using 0th Dimensional Persistent Image (PI) vectors, Bidirectional Long Short-Term Memory (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). Two ensemble models were also used to improve performances by supplementing contextual information from deep-learning models with structural information from PI vectors: BiLSTM + TDA and BERT + TDA. The results suggest that when structural information is given equal or lesser influence than contextual information, the ensemble performs better than the base models on average. This project offers a possible way of utilising TDA features to improve performances in text classification tasks, and a comparison between different models for organizations concerned with false information detection in general. |
author2 |
Fedor Duzhin |
author_facet |
Fedor Duzhin Deng, Ran |
format |
Final Year Project |
author |
Deng, Ran |
author_sort |
Deng, Ran |
title |
Topological data analysis for fake news detection |
title_short |
Topological data analysis for fake news detection |
title_full |
Topological data analysis for fake news detection |
title_fullStr |
Topological data analysis for fake news detection |
title_full_unstemmed |
Topological data analysis for fake news detection |
title_sort |
topological data analysis for fake news detection |
publisher |
Nanyang Technological University |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/156821 |
_version_ |
1759858173961830400 |