Sentiment-Tw-eng-Thelwall
Task Identifier: sentiment-tw-2012-thelwall-eng
Cluster: Sentiment Analysis
Data Type: eng
Score Metric: Accuracy
Paper/GitHub/Website URL:


RankSubmission Title Model
URL
Score
Details
1
Finetuned LMs Bernice
91.4
2
Finetuned LMs XLM-RoBERTa-Large
90.2
3
Zero-shot Chatgpt with translated prompts
90
4
Zero-shot Chatgpt
90
5
Finetuned LMs XLM-Twitter
89.6
6
Finetuned LMs InfoDCL
89.6
7
Finetuned LMs XLM-RoBERTa-Base
88.7333
8
Finetuned LMs TwHIN-BERT
85.1333
9
Finetuned LMs mBERT
79.2
10
Zero-shot BLOOMZ-P3-7B
78.4
11
five-shot in-context learning Vicuna-7B
78
12
Zero-shot Bactrian-LLaMA-7B
77.6
13
three-shot in-context learning Vicuna-7B
75.8
14
Zero-shot BLOOMZ-7B
75.6
15
Zero-shot mT0-XL
73.8
16
five-shot in-context learning LLaMA-7B
69.4
17
three-shot in-context learning LLaMA-7B
68.6
18
five-shot in-context learning mT0-XL
58.8
19
Baseline Majority
58.6703
20
three-shot in-context learning mT0-XL
58.6
21
five-shot in-context learning BLOOM-7B
57.4
22
Zero-shot Vicuna-7B
55.6
23
five-shot in-context learning BLOOMZ-P3-7B
55.2
24
three-shot in-context learning BLOOMZ-P3-7B
54.6
25
three-shot in-context learning BLOOM-7B
54.2
26
Zero-shot Alpaca-7B
54
27
Zero-shot BLOOM-7B
47.2
28
Baseline Random
47
29
three-shot in-context learning mT5-XL
45.2
30
Zero-shot Bactrian-BLOOM
45.2
31
Zero-shot LLaMA-7B
43.2
32
five-shot in-context learning mT5-XL
42.8
33
Zero-shot mT5-XL
41.2