Detection, Analysis and Visualisation of Detection, Analysis and - - PowerPoint PPT Presentation

▶
detection analysis and visualisation of detection
SMART_READER_LITE
LIVE PREVIEW

Detection, Analysis and Visualisation of Detection, Analysis and - - PowerPoint PPT Presentation

Nov 30, 2023 280 likes •596 views

Detection, Analysis and Visualisation of Detection, Analysis and Visualisation of Georeferenced Emotions Georeferenced Emotions Eva Hauthal & Dirk Burghardt Eva Hauthal & Dirk Burghardt Dresden 2013/08/26 Dresden 2013/08/26

slide-1
SLIDE 1

Detection, Analysis and Visualisation of Detection, Analysis and Visualisation of Georeferenced Emotions Georeferenced Emotions

Eva Hauthal & Dirk Burghardt Eva Hauthal & Dirk Burghardt Dresden Dresden – – 2013/08/26 2013/08/26

slide-2
SLIDE 2

Motivation

Dresden – 2013/ 08/ 26 2 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Emotional Travel Guide

http://www.apfelnews.eu/2009/07/31/das‐iphone‐als‐mobiler‐reisefuhrer‐von‐polyglott/

slide-3
SLIDE 3

Emotions

Overall emotional reaction: ∙ physiological reactions ∙ tonic posture reactions ∙ instrumental motoric reactions ∙ expressive motoric reactions ∙ expressive linguistic reactions ∙ subjective experience components

Dresden – 2013/ 08/ 26 3 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Battacchi et al. (1996) Emotion und Sprache: zur Definition der Emotion und ihren Beziehungen zu kognitiven Prozessen, dem Gedächtnis und der Sprache. Lang, Frankfurt am Main.

slide-4
SLIDE 4

4 Dresden – 2013/ 08/ 26 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Title Title Description Description Tags Tags Longitude Longitude Latitude Latitude

slide-5
SLIDE 5

Emotional Associations

Dresden – 2013/ 08/ 26 5 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

memories experiences thing, place, activity, ... emotion word

slide-6
SLIDE 6

Structuring Emotions

Dresden – 2013/ 08/ 26 6 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Arousal

negative positive arousing unarousing

Valence

Russell (1980) A circumplex model of affect. Journal of Personality and Social Psychology 39.

slide-7
SLIDE 7

ANEW & BAWL-R

Affective Norms for English Words Berlin Affective Word List ‐ Reloaded

Dresden – 2013/ 08/ 26 7 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Võ et al. (2009) The Berlin Affective Word List Reloaded (BAWL‐ R). Behavior Research Methods 41(2). Bradley & Lang (2010) Affective norms for English Words (ANEW): Stimuli, instruction manual and affective ratings. Technical Report C‐2, University of Florida.

slide-8
SLIDE 8

Emotional Analysis of Dresden

Dresden – 2013/ 08/ 26 8 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-9
SLIDE 9

Dresden – 2013/ 08/ 26 9 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Emotional Analysis of Dresden

slide-10
SLIDE 10

Considerations

1 place ≠ 1 emotion  personal preferences/experiences/memories  individual vs. collective emotions  temporal aspects

Dresden – 2013/ 08/ 26 10 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-11
SLIDE 11

< 442 words/km2 442 – 514 515 – 956 957 – 3627 3628 – 19765 19766 – 117288

Dresden – 2013/ 08/ 26 11 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

CC BY‐SA by MalteF http://de.wikipedia.org/wiki/Dresden CC BY‐NC by lyricsart http://www.flickr.com/photos/91821458@N00/76083614/

1 place ≠ 1 emotion  temporal aspects

slide-12
SLIDE 12

Dresden – 2013/ 08/ 26 12 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

< 442 words/km2 442 – 514 515 – 956 957 – 3627 3628 – 19765 19766 – 117288

CC BY‐NC by _parrish_ http://www.flickr.com/photos/_parrish_/439884019/

slide-13
SLIDE 13

Dresden – 2013/ 08/ 26 13 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

< 442 words/km2 442 – 514 515 – 956 957 – 3627 3628 – 19765 19766 – 117288

CC BY‐NC‐SA by 18сецондс http://www.flickr.com/photos/18seconds/2949364022/

slide-14
SLIDE 14

Dresden – 2013/ 08/ 26 14 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

< 442 words/km2 442 – 514 515 – 956 957 – 3627 3628 – 19765 19766 – 117288

CC BY‐NC‐SA by realname ⇋ tonal decay http://www.flickr.com/photos/19363084@N07/5459318526

 temporal aspects

slide-15
SLIDE 15

Dresden – 2013/ 08/ 26 15 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Grammatical Special Cases

happy

based on Biedermann (1969) Die deutschen Gradadverbien in synchronischer und diasynchronischer Sicht. Dissertation, Heidelberg. Quirk et al. (1985) A comprehensive grammar of the English language. Longman, London. van Os (1989) Aspekte der Intensivierung im Deutschen. Narr, Tübingen.

slide-16
SLIDE 16

Dresden – 2013/ 08/ 26 16 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Grammatical Special Cases

 degree words

based on Quirk et al. (1985) A comprehensive grammar of the English language. Longman, London.

modifying the intensity of... adjectives It was absolutely good. adverbs They love their dog very dearly. verbs He denied it strongly. nouns It was really an adventure.

slide-17
SLIDE 17

Modification of Valence and Arousal Values - Negation

e.g. unhappy  happy VO = 2.4075 AO = 3.745  unhappy Vneg = ‐2.4075 Aneg = 2.255

Dresden – 2013/ 08/ 26 17 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Vneg = ‐VO Aneg = 6 ‐ AO

slide-18
SLIDE 18

Dresden – 2013/ 08/ 26 18 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-19
SLIDE 19

Dresden – 2013/ 08/ 26 19 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-20
SLIDE 20

Dresden – 2013/ 08/ 26 20 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

„... entirely destroyed...“ „... totally destroyed...“ „... badly damaged ...“

CC BY‐SA by Deutsche Fotothek http://www.deutschefotothek.de/obj88880671.html CC BY‐SA by Deutsche Fotothek http://www.deutschefotothek.de/obj88950461.html

„... completely destroyed...“

slide-21
SLIDE 21

Future Work

Dresden – 2013/ 08/ 26 21 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Mobile Emotional Travel Guide

∙ adaptation to ‚emotional needs‘

  • f user

∙ emotional routing ∙ emotional profiles of places/sights ∙ time dependence & temporal aspects ∙ distinction individual / collective emotions ∙ visualisation

slide-22
SLIDE 22

Thanks for your attention! Thanks for your attention!

eva.hauthal@tu eva.hauthal@tu‐ ‐dresden.de dresden.de dirk.burghardt@tu dirk.burghardt@tu‐ ‐dresden.de dresden.de

slide-23
SLIDE 23

Extracting Emotions from Language

Dresden – 2013/ 08/ 26 23 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Zarafani et al. (2010) Sentiment Propagation in Social Networks: A Case Study in LiveJournal. Proceedings of Advances in social computing, Third International Conference

  • n Social Computing, Behavioral Modeling,

and Prediction. Abbasi et al. (2008) Affect Analysis of Web Forums and Blogs Using Correlation Ensembles. IEEE Transactions on Knowledge and Data Engineering 20(9).

slide-24
SLIDE 24

Dresden – 2013/ 08/ 26 24 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Title Description Tags Language Detection Lemmatisation ANEW / BAWL‐R Found Word? Word Valence Arousal Longitude Latitude Hypernym / Synonym ANEW / BAWL‐R Found Word? Word Valence Arousal Longitude Latitude yes no yes POS Tagging

Extraction of Emotions from Photo-Metadata

Sentence Segmentation

slide-25
SLIDE 25

Emotional Analysis of Dresden with Consideration of GSC

Dresden – 2013/ 08/ 26 25 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-26
SLIDE 26

Dresden – 2013/ 08/ 26 26 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Error Analysis in 50 Test Data Records

slide-27
SLIDE 27

Modification of Valence and Arousal Values - Negation

Dresden – 2013/ 08/ 26 27 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

1 2 3 4 5 ‐3 ‐2 ‐1 1 2 3

Arousal Valence

'happy' (ANEW) 'unhappy' (formula) 'unhappy' (ANEW)

slide-28
SLIDE 28

Modification of Valence and Arousal Values

Maximum Amplification Attenutation Minimum

Dresden – 2013/ 08/ 26 28 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Valence Valence Valence Valence Arousal Arousal Arousal Arousal

slide-29
SLIDE 29

Dresden – 2013/ 08/ 26 29 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -
slide-30
SLIDE 30

Modification of Valence and Arousal Values - Amplification

e.g. very happy  happy VO = 2.4075 AO = 3.745  very happy Vamp = 2.883 Aamp = 4.2125

Dresden – 2013/ 08/ 26 30 Detection, Analysis and Visualisation of Georeferenced Emotions

  • Eva Hauthal & Dirk Burghardt -

Aamp = 2AO ‐ 3 ‐ ½ ∙ |(AO ‐ 3)| ∙ (AO ‐ 3)

3‐|VO | 3 2 ‐ |AO – 3| 3 3‐|VO | 3 ∙ +1 ∙ +1 2‐|AO ‐ 3| 3

Vamp = (2 ‐ ) ∙ VO |VO | 3