Cognitive Systems Workshop & Thematic Programmes and Pump Priming Workshops, Cumberland Lodge 2012

Automatic Discovery of Patterns in News Content

author: Nello Cristianini, Department of Engineering Mathematics, University of Bristol
published: April 25, 2012, recorded: March 2012, views: 436

Slides

Slides
0:00	Automatic Discovery of Patterns in News Content
0:17	An Interesting Fact
1:55	Feedback
3:04	Cultivation Theory
3:14	An Interesting Fact
3:30	Cultivation Theory
4:14	News Content Analysis
4:31	News Coding
4:55	The MediaPatterns Project
5:43	The Problem with Large Projects...
6:29	Getting the Data
6:34	The NOAM infrastructure
6:48	The Data (1)
7:16	Analysis of the Data
7:46	Our Questions
7:59	Question 1: What Is In the News?
8:35	From Articles to Stories
8:55	People in the News
9:08	More in detail...
9:15	People in the News
9:16	M:F Ratio
9:55	Gender Bias in the Media
10:14	Detecting Topics
10:23	M:F by Topic
12:03	Validation
12:49	Observations
13:01	Question1: Which stories are covered by which outlets?
13:24	Mapping the EU Mediasphere
13:45	The Data (2)
14:09	Outlets Covering Same Stories
15:12	Linking Countries (1)
15:26	Linking Countries (2)
16:14	Explaining the Relations
17:04	Embedding: MDS on content similarity
19:56	Question 2: What Readers Want?
20:11	What Readers Want? (1)
21:03	What Readers Want? (2)
21:25	Ranking SVM
21:42	Weight vector
23:11	Average relative distances between outlets
23:46	Appeal vs. non-public-affairs bias
24:56	Question 3: Writing Style and Narrative Patterns
25:10	Writing Style
25:57	Readability
26:20	Linguistic Subjectivity
26:23	Outlet Similarity by Style
27:00	Topic Similarity by Style
27:30	Outlet Similarity by Topic Distribution
28:01	Appeal vs. Linguistic Subjectivity
28:25	Validations
28:55	Relation: style vs. demographics
29:16	Narrative analysis
30:10	Cluster (1)
30:43	NY Times Corpus, Year 2002 – crime stories
31:17	Networks of political support
31:28	NY Times Corpus, Year 2002 – crime stories
31:43	Networks of political support
31:57	Cluster (2)
32:30	Topology
33:20	Cluster (3)
33:43	Video (1)
34:14	Video (2)
35:11	Question 4: Measuring Public Mood
35:59	Time Series for Anger in Twitter Content
36:41	Time Series for Fear in Twitter Content
36:51	Rate of Mood Change by Day using the Difference in 50-day Mean
37:05	Time Series for Fear in Twitter Content
37:20	The Face of Britain...
37:46	Animation of Mood Changes
39:24	Demos
39:46	electionwatch.enm.bris.ac.uk
39:53	foundintranslation.enm.bris.ac.uk
39:57	Meme watch
39:59	celebwatch.enm.bris.ac.uk
40:03	Flu detector
40:06	Conclusions (1)
41:02	Conclusions (2)
41:28	Thanks To
41:39	MediaPatterns.enm.bristol.ac.uk

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

1 Gabriel, June 13, 2012 at 11:45 a.m.:

How can I download this video?

2 Davor (staff), July 5, 2012 at 2 p.m.:

Dear Gabriel, the videos are not downlodable at this moment, due to sever restrictions, but will be in the future, but what I suggest you to do is to download at least the slides.

Write your own review or comment:

Comment
Name
Email address
URL

make sure you have javascript enabled or clear this field:

Automatic Discovery of Patterns in News Content

Slides

Related content

Report a problem or upload files

See Also:

Link this page

Reviews and comments:

Write your own review or comment:

BIG DATA IN EUROPE

NUCLEAR DISASTER

LANGUAGE TECHNOLOGIES

INFO