Posted on: Fri Sep 24 2021

TOPIC 
FinBERT for Financial Sentiment Classification

DATE AND TIME 
Friday 24 September 2021, 3:00pm - 4:00pm

ABSTRACT 
Contextual pre-trained language models, such as BERT (Devlin et al., 2019), have made a significant breakthrough in various natural language processing (NLP) tasks by training on a large scale of unlabeled text resources. The financial sector also accumulates a large amount of financial communication text. In this work, we pre-train a financial domain-specific BERT model, FinBERT, using a large corpus of financial communication. We empirically show that FinBERT outperforms simpler NLP tasks and the generic domain BERT model. 

KEYWORDS 
Natural Language Processing, Machine Learning, Deep Learning, Textual Analysis, Sentiment Classification, Informativeness, Earnings Conference Call

SPEAKER BIOGRAPHY 
Prof. Allen Huang received his Bachelor of Science in Electronics and Information System and Technology from Peking University in 2001. He then studied the MS in Electrical & Computer Engineering in George Mason University focusing on Communications and Networking between 2001 and 2002. He graduated with a PhD in Business Administration at Duke University in 2007. Afterwards, he worked in the Quantitative Equity Strategy group in Lehman Brothers and Barclays Capital in New York until 2009. He has been working at the Department of Accounting in The Hong Kong University of Science and Technology as an Assistant and then Associate Professor since 2009. He is currently the Associate Dean in the School of Business and Management (Undergraduate Programs), the Associate Director of the Center for Business and Social Analytics, the Director of the Karen Lee Student Mentoring Center, and a Faculty Associate of the Institute for Emerging Market Studies of HKUST.

ABOUT THE WEBINAR SERIES 
This is part 2 of a 5-part webinar series featuring leading academic experts in big data analytics, information systems, machine learning, data mining, and large-scale data processing. Students interested in the CBSA-Wisers Analytics Challenge @HKUST 2021/22 are highly encouraged to attend the webinars.