lrei commited on
Commit
95f591f
1 Parent(s): e885608

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +78 -1
README.md CHANGED
@@ -8,4 +8,81 @@ widget:
8
  - text: "Thank you for your help, brave traveler."
9
  - text: "There is no creature loves me; And if I die no soul will pity me."
10
  - text: "We men are wretched things."
11
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  - text: "Thank you for your help, brave traveler."
9
  - text: "There is no creature loves me; And if I die no soul will pity me."
10
  - text: "We men are wretched things."
11
+ ---
12
+
13
+
14
+ ## Description
15
+ Literature sentences from [Project Gutenberg](https://www.gutenberg.org/). 38 emotion labels (+neutral examples). Semi-Supervised dataset.
16
+
17
+ ## Article
18
+ [Detecting Fine-Grained Emotions in Literature](https://www.mdpi.com/2076-3417/13/13/7502)
19
+
20
+ Please cite:
21
+ ```plain text
22
+ @Article{app13137502,
23
+ AUTHOR = {Rei, Luis and Mladenić, Dunja},
24
+ TITLE = {Detecting Fine-Grained Emotions in Literature},
25
+ JOURNAL = {Applied Sciences},
26
+ VOLUME = {13},
27
+ YEAR = {2023},
28
+ NUMBER = {13},
29
+ ARTICLE-NUMBER = {7502},
30
+ URL = {https://www.mdpi.com/2076-3417/13/13/7502},
31
+ ISSN = {2076-3417},
32
+ DOI = {10.3390/app13137502}
33
+ }
34
+ ```
35
+ ## Abstract
36
+ Emotion detection in text is a fundamental aspect of affective computing and is closely linked to natural language processing. Its applications span various domains, from interactive chatbots to marketing and customer service. This research specifically focuses on its significance in literature analysis and understanding. To facilitate this, we present a novel approach that involves creating a multi-label fine-grained emotion detection dataset, derived from literary sources. Our methodology employs a simple yet effective semi-supervised technique. We leverage textual entailment classification to perform emotion-specific weak-labeling, selecting examples with the highest and lowest scores from a large corpus. Utilizing these emotion-specific datasets, we train binary pseudo-labeling classifiers for each individual emotion. By applying this process to the selected examples, we construct a multi-label dataset. Using this dataset, we train models and evaluate their performance within a traditional supervised setting. Our model achieves an F1 score of 0.59 on our labeled gold set, showcasing its ability to effectively detect fine-grained emotions. Furthermore, we conduct evaluations of the model's performance in zero- and few-shot transfer scenarios using benchmark datasets. Notably, our results indicate that the knowledge learned from our dataset exhibits transferability across diverse data domains, demonstrating its potential for broader applications beyond emotion detection in literature. Our contribution thus includes a multi-label fine-grained emotion detection dataset built from literature, the semi-supervised approach used to create it, as well as the models trained on it. This work provides a solid foundation for advancing emotion detection techniques and their utilization in various scenarios, especially within the cultural heritage analysis.
37
+
38
+
39
+ ## Labels
40
+ - admiration: finds something admirable, impressive or worthy of respect
41
+ - amusement: finds something funny, entertaining or amusing
42
+ - anger: is angry, furious, or strongly displeased; displays ire, rage, or wrath
43
+ - annoyance: is annoyed or irritated
44
+ - approval: expresses a favorable opinion, approves, endorses or agrees with something or someone
45
+ - boredom: feels bored, uninterested, monotony, tedium
46
+ - calmness: is calm, serene, free from agitation or disturbance, experiences emotional tranquility
47
+ - caring: cares about the well-being of someone else, feels sympathy, compassion, affectionate concern towards someone, displays kindness or generosity
48
+ - courage: feels courage or the ability to do something that frightens one, displays fearlessness or bravery
49
+ - curiosity: is interested, curious, or has strong desire to learn something
50
+ - desire: has a desire or ambition, wants something, wishes for something to happen
51
+ - despair: feels despair, helpless, powerless, loss or absence of hope, desperation, despondency
52
+ - disappointment: feels sadness or displeasure caused by the non-fulfillment of hopes or expectations, being or let down, expresses regret due to the unfavorable outcome of a decision
53
+ - disapproval: expresses an unfavorable opinion, disagrees or disapproves of something or someone
54
+ - disgust: feels disgust, revulsion, finds something or someone unpleasant, offensive or hateful
55
+ - doubt: has doubt or is uncertain about something, bewildered, confused, or shows lack of understanding
56
+ - embarrassment: feels embarrassed, awkward, self-conscious, shame, or humiliation
57
+ - envy: is covetous, feels envy or jealousy; begrudges or resents someone for their achievements, possessions, or qualities
58
+ - excitement: feels excitement or great enthusiasm and eagerness
59
+ - faith: expresses religious faith, has a strong belief in the doctrines of a religion, or trust in god
60
+ - fear: is afraid or scared due to a threat, danger, or harm
61
+ - frustration: feels frustrated: upset or annoyed because of inability to change or achieve something
62
+ - gratitude: is thankful or grateful for something
63
+ - greed: is greedy, rapacious, avaricious, or has selfish desire to acquire or possess more than what one needs
64
+ - grief: feels grief or intense sorrow, or grieves for someone who has died
65
+ - guilt: feels guilt, remorse, or regret to have committed wrong or failed in an obligation
66
+ - indifference: is uncaring, unsympathetic, uncharitable, or callous, shows indifference, lack of concern, coldness towards someone
67
+ - joy: is happy, feels joy, great pleasure, elation, satisfaction, contentment, or delight
68
+ - love: feels love, strong affection, passion, or deep romantic attachment for someone
69
+ - nervousness: feels nervous, anxious, worried, uneasy, apprehensive, stressed, troubled or tense
70
+ - nostalgia: feels nostalgia, longing or wistful affection for the past, something lost, or for a period in one’s life, feels homesickness, a longing for one’s home, city, or country while being away; longing for a familiar place
71
+ - optimism: feels optimism or hope, is hopeful or confident about the future, that something good may happen, or the success of something
72
+ - pain: feels physical pain or is experiences physical suffering
73
+ - pride: is proud, feels pride from one’s own achievements, self-fulfillment, or from the achievements of those with whom one is closely associated, or from qualities or possessions that are widely admired
74
+ - relief: feels relaxed, relief from tension or anxiety
75
+ - sadness: feels sadness, sorrow, unhappiness, depression, dejection
76
+ - surprise: is surprised, astonished or shocked by something unexpected
77
+ - trust: trusts or has confidence in someone, or believes that someone is good, honest, or reliable
78
+
79
+ ## Dataset
80
+ [EmoLit (Zenodo)](https://zenodo.org/record/7883954)
81
+
82
+ ## Code
83
+ [EmoLit Train (Github)](https://github.com/lrei/emolit_train)
84
+
85
+ ## Models
86
+ - [LARGE](https://huggingface.co/lrei/roberta-large-emolit)
87
+ - [BASE](https://huggingface.co/lrei/roberta-base-emolit)
88
+ - [DISTILL](https://huggingface.co/lrei/distilroberta-base-emolit)