Good debt or bad debt: Detecting semantic orientations in economic texts
By Pekka Malo, Ankur Sinha, Pekka J. Korhonen, Jyrki Wallenius, P. Takala. 2013
685 citations recorded by the source corpus.
The use of robo‐readers to analyze news texts is an emerging technology trend in computational finance. Recent research has developed sophisticated financial polarity lexicons for investigating how financial sentiments relate to future company performance. However, based on experience from fields that commonly analyze sentiment, it is well known that the overall semantic orientation of a sentence may differ from that of individual words. This article investigates how semantic orientations can be better detected in financial and economic news by accommodating the overall phrase‐structure information and domain‐specific use of language. Our three main contributions are the following: (a) a human‐annotated finance phrase bank that can be used for training and evaluating alternative models; (b) a technique to enhance financial lexicons with attributes that help to identify expected direction of events that affect sentiment; and (c) a linearized phrase‐structure model for detecting contextual semantic orientations in economic texts. The relevance of the newly added lexicon features and the benefit of using the proposed learning algorithm are demonstrated in a comparative study against general sentiment models as well as the popular word frequency models used in recent financial studies. The proposed framework is parsimonious and avoids the explosion in feature space caused by the use of conventional n‐gram features.
Subfields: Artificial Intelligence, Management Science and Operations Research, Sentiment & Opinion Analysis, Economics & Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Mohit Bansal
- Quoc V. Le
- Luke S. Zettlemoyer
- Percy Liang
- Jianfeng Gao
- Graham Neubig
- Yoshua Bengio
- Yi Tay
In Management Science and Operations Research
- Samuel Rönnqvist
- Peter Sarlin
- David Stuart Rosenberg
- Steven Lu
- Vadim Dabravolski
- Ozan Irsoy
- Sebastian Gehrmann
- Shijie Wu
In Sentiment & Opinion Analysis
- Dogu Araci
- Mark Dredze
- Ingrid E. Fisher
- Allen Huang
- MA Uy
- Margaret R. Garnsey
- Yi Yang
- Mark E. Hughes
In Economics & Operations Research
Citations in the corpus
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? (2022, neutral): “We include 26 datasets as follows: fi-nancial_phrasebank (Malo et al., 2014), poem_sentiment (Sheng and Uthus, 2020), medical_questions_pairs (McCreery et al., 2020), glue-mrpc (Dolan and Brockett, 2005), glue-wnli (Levesque et al., 2012), climate_fever (Diggel-mann et al., 2020), glue-rte (Dagan et…”
- SplitNN-driven Vertical Partitioning (2020, background): “We use Financial PhraseBank to analyze the effect of splitting the dataset across a higher number of clients.”
- BloombergGPT: A Large Language Model for Finance (2023, methodology): “Like with FPB, we create our own splits including microblogs and news, and use a 5-shot setup, reporting weighted F1.”
- Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (2022, methodology): “…(Levesque et al., 2012) 635 71 2 super_glue-cb (de Marneffe et al., 2019) 250 56 3 trec (Voorhees and Tice, 2000) 5,452 500 5 financial_phrasebank (Malo et al., 2014) 1,181 453 3 poem_sentiment (Sheng and Uthus, 2020) 843 105 3 medical_questions_pairs (McCreery et al., 2020) 2,438 610 2 sick…”
- Bank distress in the news: Describing events through deep learning (2016, background): “[22] explore a linguistically more sophisticated approach that models financial sentiment compositionally, although without semantic generalization, supervised by a custom data set of annotated phrases.”
- Natural Language Processing in Accounting, Auditing and Finance: A Synthesis of the Literature with a Roadmap for Future Research (2016, methodology): “…2011), character n-gram (CNG) (Butler & Keselj, 2009), term frequencyinverse document frequency (TF-IDF) (Peramunetilleke & Wong, 2002), categorical k-nearest neighbour (CKNN) (Huang & Li, 2011), the linearized phrase structure (LPS) model (Malo et al., 2014) and kernel methods (Cecchini, 2005).”
- SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News (2017, background): “(Malo et al., 2014b) present the Financial Phrase Bank, a resource containing around 5000 sentences from English-language news about companies listed on the Helsinki stock exchange.”
- Larger language models do in-context learning differently (2023, methodology): “…et al., 2017; Wang et al., 2018, QQP); Textual Entailment Recognition (Dagan et al., 2006; Wang et al., 2019, RTE); Financial Sentiment Analysis (Malo et al., 2014, FP); and Hate Speech Detection (Mollas et al., 2020, ETHOS).1 2.2 MODELS We perform experiments on five language model families as…”
- FinBERT: Financial Sentiment Analysis with Pre-trained Language Models (2019, methodology): “LPS [17], HSC [8] and FinSSLX [15] results are taken from their respective papers.”
- FinBERT: A Pretrained Language Model for Financial Communications (2020, background): “Financial Phrase Bank is a public dataset for financial sentiment classification (Malo et al., 2014).”
- Deep learning bank distress from news and numerical financial data (2017, methodology): “(Malo et al. 2014) provide an example of a more sophisticated supervised corpus-based approach, in which they apply a framework modelling financial sentiment expressions by a custom data set of annotated phrases.”