7 |
Hybrid Hashtags: #YouKnowYoureAKiwiWhen Your Tweet Contains Māori and English
|
|
|
|
In: Front Artif Intell (2020)
|
|
BASE
|
|
Show details
|
|
9 |
Hybrid Hashtags: #YouKnowYoureAKiwiWhen Your Tweet Contains Māori and English
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Māori loanwords: a corpus of New Zealand English tweets
|
|
|
|
In: Vocab@Leuven 2019 (2019)
|
|
BASE
|
|
Show details
|
|
13 |
WASSA-2017 shared task on emotion intensity
|
|
|
|
In: WASSA 2017 (2017)
|
|
BASE
|
|
Show details
|
|
15 |
Acquiring and Exploiting Lexical Knowledge for Twitter Sentiment Analysis
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Determining word–emotion associations from tweets by multi-label classification
|
|
|
|
In: WI'16 (2016)
|
|
BASE
|
|
Show details
|
|
17 |
Building a Twitter opinion lexicon from automatically-annotated tweets
|
|
|
|
BASE
|
|
Show details
|
|
18 |
From opinion lexicons to sentiment classification of tweets and vice versa: a transfer learning approach
|
|
|
|
In: WI'16 (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Annotate-Sample-Average (ASA): A New Distant Supervision Approach for Twitter Sentiment Analysis
|
|
|
|
In: 22nd European Conference on Artificial Intelligence (ECAI) (2016)
|
|
Abstract:
The classification of tweets into polarity classes is a popular task in sentiment analysis. State-of-the-art solutions to this problem are based on supervised machine learning models trained from manually annotated examples. A drawback of these approaches is the high cost involved in data annotation. Two freely available resources that can be exploited to solve the problem are: 1) large amounts of unlabelled tweets obtained from the Twitter API and 2) prior lexical knowledge in the form of opinion lexicons. In this paper, we propose Annotate-Sample-Average (ASA), a distant supervision method that uses these two resources to generate synthetic training data for Twitter polarity classification. Positive and negative training instances are generated by sampling and averaging unlabelled tweets containing words with the corresponding polarity. Polarity of words is determined from a given polarity lexicon. Our experimental results show that the training data generated by ASA (after tuning its parameters) produces a classifier that performs significantly better than a classifier trained from tweets annotated with emoticons and a classifier trained, without any sampling and averaging, from tweets annotated according to the polarity of their words.
|
|
Keyword:
Artificial Intelligence; Computer Science; Machine learning; Science & Technology; Technology
|
|
URL: https://hdl.handle.net/10289/10753 https://doi.org/10.3233/978-1-61499-672-9-498
|
|
BASE
|
|
Hide details
|
|
20 |
From unlabelled tweets to Twitter-specific opinion words
|
|
|
|
In: SIGIR '15 (2015)
|
|
BASE
|
|
Show details
|
|
|
|