[Seminar] "Learning from social data to study human behaviour" by Dr. Scott A. Hale

Date

Friday, November 1, 2019 - 14:30 to 15:30

Location

Meeting room D015, Lab1 Bldg.

Description

Dear all,

Neural Computation Unit (Doya Unit) would like to invite you to a seminar as follows.

Date: Friday, November 1, 2019
Time: 14:30 – 15:30
Venue: Meeting room D015, Lab1 Bldg.

Speaker: Dr. Scott A.Hale
                Oxford Internet Institute, University of Oxford

Title:
Learning from social data to study human behaviour
 
Abstract:
We generate unprecedented quantities of data through our online social interactions that, through new computational approaches, enable social science research at scale. A key challenge for social scientists, however, is the non-representative nature of online data. In this talk, Dr Scott A. Hale describes a new multimodal deep neural architecture for joint classification of age, gender, and organization-status of social media users that operates in 32 languages. This method uses both image and text data from social media profiles and substantially outperforms current state of the art while also reducing algorithmic bias. The results can be used to identify and reduce representation bias in social media data. Dr Hale will also briefly discuss his research analysing semantic change on social media using word embeddings, tracking the spread of memes using image hashing, and analysing the similarity of television news across languages.

Bio:
Dr Scott A. Hale is a Senior Research Fellow at the Oxford Internet Institute, University of Oxford, Director of Research at Meedan, and a Fellow at the Alan Turing Institute. His cross-disciplinary research develops and applies new computational science techniques to social science questions and puts the results into practice with industry and policy partners. He is particularly interested in multilingual natural language processing, machine learning, agenda setting, and antisocial behaviour (e.g., hate speech) and has a strong track record in building tools and teaching programmes that enable wider access new methods and forms of data.

We hope to see many of you at the seminar.

Sincerely,
Neural Computation Unit
Contact: ncus@oist.jp

All-OIST Category: 

Intra-Group Category


Subscribe to the OIST Calendar: Right-click to download, then open in your calendar application.