FedNLP: An Interpretable NLP System to Decode Federal Reserve Communications

Lee, Jean; Youn, Hoyoul Luis; Stevens, Nicholas; Poon, Josiah; Han, Soyeon Caren

doi:10.1145/3404835.3462785

Cited by 6 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Federated learning (FL) [18,19] is a novel machine learning paradigm that performs learning in a distributed way. In federated learning, the data owner trains the model locally to avoid data leakage of clients.…”

Section: Introductionmentioning

confidence: 99%

Defending Privacy Inference Attacks to Federated Learning for Intelligent IoT with Parameter Compression

Zhu

Cao

Ren

et al. 2023

Security and Communication Networks

View full text Add to dashboard Cite

Federated learning has been popularly studied with people’s increasing awareness of privacy protection. It solves the problem of privacy leakage by its ability that allows many clients to train a collaborative model without uploading local data collected by Internet of Things (IoT) devices. However, there are still threats of privacy leakage in federated learning. The privacy inference attacks can reconstruct the privacy data of other clients based on GAN from the parameters in the process of iterations for global models. In this work, we are motivated to prevent GAN-based privacy inference attacks in federated learning. Inspired by the idea of gradient compression, we propose a defense method called Federated Learning Parameter Compression (FLPC) which can reduce the sharing of information for privacy protection. It prevents attackers from recovering the private information of victims while maintaining the accuracy of the global model. Extensive experimental results demonstrated that our method is effective in the prevention of GAN-based privacy inferring attacks. In addition, based on the experimental results, we propose a norm-based metric to assess the performance of privacy-preserving.

show abstract

Section: Introductionmentioning

confidence: 99%

Defending Privacy Inference Attacks to Federated Learning for Intelligent IoT with Parameter Compression

Zhu

Cao

Ren

et al. 2023

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Natural Language Processing (NLP) in finance is a growing research area and has attracted considerable attention from both academics and industry. Researchers are seeking to analyze financial sentiment collected from social media (Cortis et al 2017;Chen, Huang, and Chen 2020;Xing et al 2020) or news (Du and Tanaka-Ishii 2020;Lee et al 2021), and combine financial text mining with historical price data for stock market prediction (Sawhney et al 2020). In particular, public mood and financial sentiment play a significant role in investment decisions as is explored in behavioral finance (Griffith, Najand, and Shen 2020;Zaleskiewicz and Traczyk 2020); furthermore, social media messages have been studied as useful resources for detecting sentiment in NLP research (Ge et al 2020).…”

Section: Introductionmentioning

confidence: 99%

StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series

Lee¹,

Youn²,

Poon³

et al. 2023

Preprint

View full text Add to dashboard Cite

There has been growing interest in applying NLP techniques in the financial domain, however, resources are extremely limited. This paper introduces StockEmotions, a new dataset for detecting emotions in the stock market that consists of 10k English comments collected from StockTwits, a financial social media platform. Inspired by behavioral finance, it proposes 12 fine-grained emotion classes that span the roller coaster of investor emotion. Unlike existing financial sentiment datasets, StockEmotions presents granular features such as investor sentiment classes, fine-grained emotions, emojis, and time series data. To demonstrate the usability of the dataset, we perform a dataset analysis and conduct experimental downstream tasks. For financial sentiment/emotion classification tasks, DistilBERT outperforms other baselines, and for multivariate time series forecasting, a Temporal Attention LSTM model combining price index, text, and emotion features achieves the best performance than using a single feature.

show abstract

“…In recent developments, Embeddings from Language Models (ELMo) (Peters et al, 2018) was introduced to solve the problem of polysemy following an advancement that led to BERT (Devlin et al, 2019) (Chen, 2021;Lee et al, 2021;Mishev et al, 2020;Sonkiya et al, 2021). Sonkiya et al (2021) finds that their Generative Adversarial Network, which uses the sentiment of news and headlines using FinBERT, outperformed traditional time series models like ARIMA.…”

Section: Literature Reviewmentioning

confidence: 99%

Unsupervised Text Mining Techniques for Forecasting Crude Oil

Hazen¹

View full text Add to dashboard Cite

FedNLP: An Interpretable NLP System to Decode Federal Reserve Communications

Cited by 6 publications

References 21 publications

Defending Privacy Inference Attacks to Federated Learning for Intelligent IoT with Parameter Compression

Defending Privacy Inference Attacks to Federated Learning for Intelligent IoT with Parameter Compression

StockEmotions: Discover Investor Emotions for Financial Sentiment Analysis and Multivariate Time Series

Unsupervised Text Mining Techniques for Forecasting Crude Oil

Contact Info

Product

Resources

About