• Home
  • HKU CDS Distinguished Lecture Series: Multimodal LLMs as Social Media Analysis Engines

HKU CDS Distinguished Lecture Series: Multimodal LLMs as Social Media Analysis Engines

spot

25 Feb 2025

HKU CDS Distinguished Lecture Series: Multimodal LLMs as Social Media Analysis Engines (20 March 2025)

CDS has launched its Distinguished Lecture Series, where esteemed scholars from around the world will share their expertise and insights in the areas of computer science, data science, artificial intelligence, and statistics.

Register Now
black spot
image

The School of Computing and Data Science (CDS) is thrilled to announce the launch of its Distinguished Lecture Series. We are honoured to host distinguished scholars at HKU who will share their expertise and insights in the areas of computer science, data science, artificial intelligence, and statistics.

 

Our inaugural Distinguished Lecture, titled “Multimodal LLMs as Social Media Analysis Engines”, will be presented by Professor Jiebo LUO, Albert Arendt Hopeman Professor of Engineering and Professor of Computer Science at the University of Rochester.

 

Please find the event details below:

 

Date: 20 March 2025 (Thursday)
Time: 11:30 am – 12:30 pm
Venue: Rayson Huang Lecture Theatre, Main Campus, HKU
Medium: English

 

Registration: https://shorturl.at/NF3Sw

 

Abstract

 

This lecture will discuss the capabilities of Multimodal Large Multimodal Models (MLMMs) in analysing social media content, which combines text, images, videos, and sometimes audio. The research explores how MLMMs perform in tasks such as sentiment analysis, hate speech detection, fake news identification, demographic inference, and political ideology detection.

 

The study demonstrates GPT-4V’s effectiveness in understanding multimodal social media content, highlighting strengths such as joint understanding of image-text pairs, contextual and cultural awareness, and extensive commonsense knowledge. Despite challenges like the hallucination problem and difficulties with multilingual comprehension and generalising to latest social media trends, the research suggests strategies to improve performance on specific tasks.

 

About the Speaker

 

Professor Jiebo Luo has a prolific career at the University of Rochester and Kodak Research Laboratories. He has authored over 600 technical papers and holds over 90 U.S. patents. His research interests include computer vision, NLP, machine learning, data mining, computational social science, and digital health. Professor Luo has served on the editorial boards of numerous scientific journals, and he is a Fellow of ACM, AAAI, IEEE, AIMBE, IAPR, and SPIE, as well as a Member of Academia Europaea and the US National Academy of Inventors (NAI).

 

All are welcome to attend. For any query, please contact us at cdsnews@hku.hk.