Fortia-FBK at SemEval-2017 Task 5: Bullish or Bearish? Inferring Sentiment towards Brands from Financial News Headlines

Abstract

In this paper, we describe a methodology to infer Bullish or Bearish sentiment towards companies/brands. More specifically, our approach leverages affective lexica and word embeddings in combination with convolutional neural networks to infer the sentiment of financial news headlines towards a target company. Such architecture was used and evaluated in the context of the SemEval 2017 challenge (task 5, subtask 2), in which it obtained the best performance.

Knowledge-Enriched Two-Layered Attention Network for Sentiment Analysis

“…Table 1 shows evaluation of our various models. Team ECNU (Lan et al, 2017) and Fortia-FBK (Mansar et al, 2017) were the top systems for sub-tracks 1 and 2 respectively. Team ECNU and Fortia-FBK reported a cosine similarity of 0.777 and 0.745 for sub-tracks 1 and 2 respectively.…”

Assessing Regression-Based Sentiment Analysis Techniques in Financial Texts

“…Regarding sentiment analysis hybrid approach, previous work combined the GloVe word embeddings with the VADER lexicon [Hutto and Gilbert 2014] information into a CNN model [Mansar et al 2017].…”

SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News

“…The systems that ranked first (Mansar et al, 2017) and second (Kar et al, 2017) both adopted a Hybrid (DL, Lex) technique, whereas an ML technique was used by the system in rank three.…”

“…The Deep Learning-based techniques made use of the following algorithms: • RNN : Bidirectional Long Short-Term Memory (BLSTM) -adopted by Moore and Rayson (2017) • Bidirectional Gated Recurrent Unit (Bi-GRU) -adopted by Kar et al (2017) The CNN algorithm was the most popular amongst all Deep Learning-based techniques, with both systems ranking first (Mansar et al, 2017) and second (Kar et al, 2017) using it.…”

“…• Yelp Restaurant Sentiment Lexicon -adopted by Chen et al (2017) • Amazon Laptop Sentiment Lexicon -adopted by Chen et al (2017) • Macquarie Semantic Orientation Lexiconadopted by Chen et al (2017) • Harvard's General Inquirer Lexicon -adopted by Nasim (2017) • IMDB -adopted by Jiang et al (2017) • AFINN -adopted by Jiang et al (2017) • DepecheMood Affective Lexicon (Staiano and Guerini, 2014) -adopted by Mansar et al (2017) • Amazon Product Reviews 16 -adopted by John and Vechtomova (2017) • Financial Phrasebank (Malo et al, 2014a) -adopted by John and Vechtomova (2017) • Corpus of Business News -adopted by Pivovarova et al (2017) In total, four lexica listed above are the ones mostly used (all by 4 participants each): (i) the Loughran and McDonald Sentiment Word, (ii) SentiWordNet, (iii) Opinion Lexicon and (iv) Harvard's General Inquirer Lexicon. Unlike the case in track 1, none of the participants ranked first till third used one of these four lexica.…”