Geodesy

Random forest

World Wide Web

Benchmark (surveying)

Emoji

Set (abstract data type)

Computer science

Language model

Natural language processing

Mathematics

Geography

Social media

Domain (mathematical analysis)

Mathematical analysis

Artificial intelligence

Geometry

Information retrieval

Point (geometry)

Programming language

Training set

Sentiment analysis

Machine learning

The experimental landscape in natural language processing for social media is too fragmented. Each year, new shared tasks and datasets are proposed, ranging from classics like sentiment analysis to irony detection or emoji prediction. Therefore, it is unclear what the current state of the art is, as there is no standardized evaluation protocol, neither a strong set of baselines trained on such domain-specific data. In this paper, we propose a new evaluation framework (TweetEval) consisting of seven heterogeneous Twitter-specific classification tasks. We also provide a strong set of baselines as starting point, and compare different language modeling pre-training strategies. Our initial experiments show the effectiveness of starting off with existing pre-trained generic language models, and continue training them on Twitter corpora.

TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification