The Stock Sonar — Sentiment Analysis of Stocks Based on a Hybrid Approach

Feldman, Ronen; Rosenfeld, Benjamin; Bar-Haim, Roy; Fresko, Moshe

doi:10.1609/aaai.v25i2.18854

Cited by 81 publications

(9 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, if p and n refer to the weighted sum of positive and negative sentiments associated with the subject, the weighted average is given by (p−n)/(p+n+1). This is similar to (Feldman et al 2011) and we empirically show that such a representation of opinion expression results in identifying better opinion clusters. Note that if an opinion subject is present in a sentence, all the words present in that sentence would influence the weighted computation of sentiment score of the subject.…”

Section: Disambiguated Concept Representationsupporting

confidence: 85%

Towards Quantifying the Distance between Opinions

Gurukar

Ajwani

Dutta³

et al. 2020

ICWSM

View full text Add to dashboard Cite

Increasingly, critical decisions in public policy, governance, and business strategy rely on a deeper understanding of the needs and opinions of constituent members (e.g. citizens, shareholders). While it has become easier to collect a large number of opinions on a topic, there is a necessity for automated tools to help navigate the space of opinions. In such contexts understanding and quantifying the similarity between opinions is key. We find that measures based solely on text similarity or on overall sentiment often fail to effectively capture the distance between opinions. Thus, we propose a new distance measure for capturing the similarity between opinions that leverages the nuanced observation – similar opinions express similar sentiment polarity on specific relevant entities-of-interest. Specifically, in an unsupervised setting, our distance measure achieves significantly better Adjusted Rand Index scores (up to 56x) and Silhouette coefficients (up to 21x) compared to existing approaches. Similarly, in a supervised setting, our opinion distance measure achieves considerably better accuracy (up to 20% increase) compared to extant approaches that rely on text similarity, stance similarity, and sentiment similarity.

show abstract

Section: Disambiguated Concept Representationsupporting

confidence: 85%

Towards Quantifying the Distance between Opinions

Gurukar

Ajwani

Dutta³

et al. 2020

ICWSM

View full text Add to dashboard Cite

show abstract

“…At present, there have been few studies focusing on event extraction from stock announcements [12,19,21], and more studies are focusing on event extraction from financial news. We select some representative related studies and list them in Table 3 for comparison.…”

Section: Comparison To Existing Resultsmentioning

confidence: 99%

“…The Stock Sonar project expert-created event typology identified eight event types: "Legal", "Analyst Recommendation", "Financial", "Stock Price Change", "Deals", "Mergers and Acquisitions", "Partnerships", "Product", and "Employment" [12]. The author focused on the event types in stock announcement news, but the number of designed event types are small and the coverage is not wide.…”

Section: Related Researchmentioning

confidence: 99%

Fine-Grained Classification of Announcement News Events in the Chinese Stock Market

et al. 2022

View full text Add to dashboard Cite

Determining the event type is one of the main tasks of event extraction (EE). The announcement news released by listed companies contains a wide range of information, and it is a challenge to determine the event types. Some fine-grained event type frameworks have been built from financial news or stock announcement news by domain experts manually or by clustering, ontology or other methods. However, we think there are still some improvements to be made based on the existing results. For example, a legal category has been created in previous studies, which considers violations of company rules and violations of the law the same thing. However, the penalties they face and the expectations they bring to investors are different, so it is more reasonable to consider them different types. In order to more finely classify the event type of stock announcement news, this paper proposes a two-step method. First, the candidate event trigger words and co-occurrence words satisfying the support value are extracted, and they are arranged in the order of common expressions through the algorithm. Then, the final event types are determined using three proposed criteria. Based on the real data of the Chinese stock market, this paper constructs 54 event types (p = 0.927, f = 0.946), and some reasonable and valuable types have not been discussed in previous studies. Finally, based on the unilateral trading policy of the Chinese stock market, we screened out some event types that may not be valuable to investors.

show abstract

“…3. Sentiment score: The approach to determine the article score was similar to Feldman et al (2011). The number of positive and negative sentiment words in the text were summed.…”

Section: Sentiment Scoringmentioning

confidence: 99%

News sentiment and international equity markets during BREXIT period: A textual and connectedness analysis

2022

View full text Add to dashboard Cite

This study used textual analysis of 34,209 news articles to quantify news sentiment into three main clusters-positive, negative and neutral-before analysing how they co-move with international equity indices, using the time-varying connectedness of Yilmaz (2009, 2012). Better understanding of the spillover of news sentiment to stock markets could aid the decision-making of institutional investors when strong uncertainty is present across major economies. We found that limited spillover from news sentiment to equity markets existed for both the European and international indices examined in the analysis, with spillover being stronger among smaller subsets of news articles more relevant for financial market participants. Additionally, the results indicated that, in the full sample, directional spillover was especially strong in times of larger uncertainty concerning BREXIT developments, whereas the smaller subsets, although also displaying stronger spillover during BREXIT uncertainty, revealed additional spillover peaks at times less related to major BREXIT developments. Differentiation between news about UKbased and EU-based companies also showed less spillover from news sentiment regarding EU-based companies, possibly implying that investors saw BREXIT developments as less relevant for the latter.

show abstract

The Stock Sonar — Sentiment Analysis of Stocks Based on a Hybrid Approach

Cited by 81 publications

References 8 publications

Towards Quantifying the Distance between Opinions

Towards Quantifying the Distance between Opinions

Fine-Grained Classification of Announcement News Events in the Chinese Stock Market

News sentiment and international equity markets during BREXIT period: A textual and connectedness analysis

Contact Info

Product

Resources

About