TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news

Leon Rotim, Martin Tutek, Jan Šnajder


Abstract
This paper describes our system for fine-grained sentiment scoring of news headlines submitted to SemEval 2017 task 5–subtask 2. Our system uses a feature-light method that consists of a Support Vector Regression (SVR) with various kernels and word vectors as features. Our best-performing submission scored 3rd on the task out of 29 teams and 4th out of 45 submissions with a cosine score of 0.733.
Anthology ID:
S17-2148
Volume:
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Steven Bethard, Marine Carpuat, Marianna Apidianaki, Saif M. Mohammad, Daniel Cer, David Jurgens
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
866–871
Language:
URL:
https://aclanthology.org/S17-2148
DOI:
10.18653/v1/S17-2148
Bibkey:
Cite (ACL):
Leon Rotim, Martin Tutek, and Jan Šnajder. 2017. TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), pages 866–871, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
TakeLab at SemEval-2017 Task 5: Linear aggregation of word embeddings for fine-grained sentiment analysis of financial news (Rotim et al., SemEval 2017)
Copy Citation:
PDF:
https://aclanthology.org/S17-2148.pdf