Overview of methods and approaches in Social Sciences thumbnail
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Overview of methods and approaches in Social Sciences

Published on Jul 27, 20171714 Views

Related categories

Chapter list

Doing Text Analytics for Digital Humanities and Social Sciences with CLARIN00:00
NLP for computational social science00:10
Traditional data sources in the social sciences - 100:19
Traditional data sources in the social sciences - 200:43
Traditional data sources in the social sciences - 300:49
Big social and cultural data - 101:18
Big social and cultural data - 201:44
Today: Focus on methodological challenges02:22
NLP for theory building and explanation03:01
Exploration vs prediction03:07
Opinions..04:17
Explanation vs. prediction05:20
NLP for theory building and explanation - 106:45
NLP for theory building and explanation - 207:11
Cultural fit in organisations07:12
Cultural fit in organisations II08:29
Cultural fit in organisations III09:53
Cultural fit in organisations IV11:00
NLP for theory building and explanation - 312:35
Topic modeling12:44
LDA example13:48
Topic modeling examples14:09
Grounded theory14:43
Topic modeling vs grounded theory I15:38
Topic modeling vs grounded theory II16:21
Topic modeling vs grounded theory III17:08
NLP for theory building and explanation - 418:31
Movember18:43
Scaling up the Social Identity Model of Collective Action - 119:10
Scaling up the Social Identity Model of Collective Action - 220:13
Scaling up the Social Identity Model of Collective Action - 320:24
Philip Bloom21:02
Automatic classification of Movember profiles21:18
Findings22:01
Alternative22:59
NLP for theory building and explanation - 523:51
Interpretable models24:05
Making the model more interpretable24:45
Extract an interpretable model25:44
Global vs. local explanation27:10
Interpreting neural networks for politeness prediction I - 128:03
Interpreting neural networks for politeness prediction I - 228:58
Local explanation: LIME I29:42
Local explanation: LIME II31:19
Local explanation: LIME III32:01
Interpretable models?32:38
Causality I33:09
Causality II33:56
Causality III34:15
Summary - 134:35
References - 135:07
Data bias35:14
Representativeness & bias35:33
Data source selection I36:23
Data source selection II38:22
Data source selection III39:26
Bias in Twitter: demographics40:01
Bias in Twitter: language I41:30
Bias in Twitter: language II42:20
Bias Twitter: sampling42:54
Google books I - 145:49
Google books I - 246:21
Google books II46:41
Google books III47:39
Google books IV48:03
Summary - 248:51
References - 249:28
Small vs. big data49:31
Making big data small again49:41
NLP for small data50:19
Supporting small data analysis50:50
References - 352:23
Ethical challenges52:26
Privacy I52:35
Privacy II53:19
Data representativeness54:06
POS taggers: age groups54:52
POS taggers: AAVE55:37
Language identification: AAE56:12
Perpetuation of bias: word embeddings I57:29
Perpetuation of bias: word embeddings II59:09
Finder gender stereotype analogies01:00:08
Detecting bias - 101:01:23
Detecting bias - 201:01:49
Perpetuation of bias in sentiment analysis01:02:16
Reinforcing stereotypes? gender in NLP I01:03:13
Reinforcing stereotypes? gender in NLP II01:04:01
Reinforcing stereotypes? gender in NLP III01:04:39
Reinforcing stereotypes? gender in NLP IV01:05:59
Reinforcing stereotypes? gender in NLP V01:07:00
References: critical look on gender in NLP01:07:53
Conclusion - 101:07:56
Conclusion - 201:08:15
Conclusion - 301:08:18
Questions?01:08:47