Home > Research > Publications & Outputs > Lancaster A at SemEval-2017 Task 5: Evaluation ...

Electronic data

  • lancaster-semeval-2017

    Accepted author manuscript, 155 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published

Standard

Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter : predicting sentiment from financial news headlines. / Moore, Andrew; Rayson, Paul Edward.

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017). Stroudsburg, PA : Association for Computational Linguistics, 2017. p. 581-585.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Harvard

Moore, A & Rayson, PE 2017, Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines. in Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017). Association for Computational Linguistics, Stroudsburg, PA, pp. 581-585. https://doi.org/10.18653/v1/S17-2095

APA

Moore, A., & Rayson, P. E. (2017). Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines. In Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017) (pp. 581-585). Association for Computational Linguistics. https://doi.org/10.18653/v1/S17-2095

Vancouver

Moore A, Rayson PE. Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines. In Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017). Stroudsburg, PA: Association for Computational Linguistics. 2017. p. 581-585 https://doi.org/10.18653/v1/S17-2095

Author

Moore, Andrew ; Rayson, Paul Edward. / Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter : predicting sentiment from financial news headlines. Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017). Stroudsburg, PA : Association for Computational Linguistics, 2017. pp. 581-585

Bibtex

@inproceedings{63f61df86c9a41dc83f965f78dd5744c,
title = "Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter: predicting sentiment from financial news headlines",
abstract = "This paper describes our participation in Task 5 track 2 of SemEval 2017 to predict the sentiment of financial news headlines for a specific company on a continuous scale between -1 and 1. We tackled the problem using a number of approaches, utilising a Support Vector Regression (SVR) and a Bidirectional Long Short-Term Memory (BLSTM). We found an improvement of 4-6% using the LSTM model over the SVR and came fourth in the track. We report a number of different evaluations using a finance specific word embedding model and reflect on the effects of using different evaluation metrics.",
author = "Andrew Moore and Rayson, {Paul Edward}",
year = "2017",
month = aug
day = "4",
doi = "10.18653/v1/S17-2095",
language = "English",
isbn = "9781945626555",
pages = "581--585",
booktitle = "Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017)",
publisher = "Association for Computational Linguistics",

}

RIS

TY - GEN

T1 - Lancaster A at SemEval-2017 Task 5: Evaluation metrics matter

T2 - predicting sentiment from financial news headlines

AU - Moore, Andrew

AU - Rayson, Paul Edward

PY - 2017/8/4

Y1 - 2017/8/4

N2 - This paper describes our participation in Task 5 track 2 of SemEval 2017 to predict the sentiment of financial news headlines for a specific company on a continuous scale between -1 and 1. We tackled the problem using a number of approaches, utilising a Support Vector Regression (SVR) and a Bidirectional Long Short-Term Memory (BLSTM). We found an improvement of 4-6% using the LSTM model over the SVR and came fourth in the track. We report a number of different evaluations using a finance specific word embedding model and reflect on the effects of using different evaluation metrics.

AB - This paper describes our participation in Task 5 track 2 of SemEval 2017 to predict the sentiment of financial news headlines for a specific company on a continuous scale between -1 and 1. We tackled the problem using a number of approaches, utilising a Support Vector Regression (SVR) and a Bidirectional Long Short-Term Memory (BLSTM). We found an improvement of 4-6% using the LSTM model over the SVR and came fourth in the track. We report a number of different evaluations using a finance specific word embedding model and reflect on the effects of using different evaluation metrics.

U2 - 10.18653/v1/S17-2095

DO - 10.18653/v1/S17-2095

M3 - Conference contribution/Paper

SN - 9781945626555

SP - 581

EP - 585

BT - Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017)

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

ER -