A Lexicon Enhanced Collaborative Network for targeted financial sentiment analysis. Issue 2 (March 2023)

• Record Type: Journal Article
• Authors: Shang, Lili; Xi, Hao; Hua, Jiaojiao; Tang, Huayun; Zhou, Jilei
• Is Part Of: Information processing & management. Volume 60:Issue 2(2023)
• Publication Date: 2023-03
• Subjects: Targeted financial sentiment analysis -- Attention mechanism -- Lexicon-based method -- Deep learning -- Natural language processing; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2022.103187
• Languages: English
• ISSNs: 0306-4573

Abstract

Highlights: A novel methodology is proposed for fine-grained targeted financial sentiment analysis. LECN is a unified and collaborative framework to capture connections between the target extraction (TE) and sentiment analysis (SA). A dynamic weighting strategy based on sentiment lexicons enables the model to well determine sentiment polarities. A message selective-passing mechanism enhances collaborative effects between TE and SA tasks. Experimental results on four financial datasets demonstrate the proposed model outperforms competitive baselines. Abstract: The increasing interest around emotions in online texts creates the demand for financial sentiment analysis. Previous studies mainly focus on coarse-grained document-/sentence-level sentiment analysis, which ignores different sentiment polarities of various targets (e.g., company entities) in a sentence. To fill the gap, from a fine-grained target-level perspective, we propose a novel Lexicon Enhanced Collaborative Network (LECN) for targeted sentiment analysis (TSA) in financial texts. In general, the model designs a unified and collaborative framework that can capture the associations of targets and sentiment cues to enhance the overall performance of TSA. Moreover, the model dynamically incorporates sentiment lexicons to guide the sentiment classification, which cultivates the model faculty of understanding financial expressions. In addition, the model introduces a message selective-passing mechanism to adaptively control the information flow between two tasks, thereby improving the collaborative effects. To verify the effectiveness of LECN, we conduct experiments on four financial datasets, including SemEVAL2017 Task5 subset1, SemEVAL2017 Task5 subset2, FiQA 2018 Task1, and Financial PhraseBank. Results show that LECN achieves improvements over the state-of-art baseline by 1.66 p.p., 1.47 p.p., 1.94 p.p., and 1.88 p.p. in terms of F1-score. A series of further analyses also indicate that LECN has a better capacity for comprehending domain-specific expressions and can achieve the mutually beneficial effect between tasks.