What Investors Ought to Know About Knowledge Graphs: The Core of Text Analysis
June 2, 2022
•
5 mins read
Researching and analyzing investment opportunities can be challenging for asset management—private equity and hedge fund portfolio managers, researchers, and analysts—because, of course, you want to make sure that you're a good steward of your client's investments.
And when you find and source data, such as traditional or alternative data, you also want to make sure it's reliable and that the methods used to gather it are tried and true.
This article aims to give you an inside look into SESAMm's knowledge graph—one of the key reasons SESAMm's NLP-derived alternative data is reliable and trusted. We'll explain what a knowledge graph is, why it's important, how it works, and what makes SESAMm's knowledge graph unique.
What is a knowledge graph?
A knowledge graph is a digital representation of a network of real-world entities, the foundation of a search engine or question-answering service. This structured data model puts the schema in context through linking and semantic metadata, providing a framework for data integration, analytics, unification, and sharing. In other words, it's like a map and legend, with the legend labeling the concepts, entities, and events and the map connecting and identifying their relationships. These details are stored in a graph database and visualized as a graph representation, hence the term knowledge graph.
Fun fact: The expression, knowledge graph, gained popularity after Google used it in 2012 to name their semantic network.
Two types of knowledge graphs
There are two general types of knowledge graphs: open and private. Open knowledge graphs are open to the public. They're created and made available by organizations such as Wikidata, DBpedia, and Yago. Private knowledge graphs are often only used by organizations that create them, like Google, WolframAlpha, Facebook, and SESAMm (of course). Some offer them up for a fee or subscription, such as Crunchbase and OpenCorporates.
Why a knowledge graph is important
Knowledge graphs are important because they equip us with a model to see how everything relates from a big-picture view, creating new knowledge. Its benefits include:
Incorporating disparate data sources, avoiding data silos
From a data science and artificial intelligence (AI) perspective, knowledge graphs provide machine-readable details, adding context and depth to data-driven AI techniques such as machine learning. Using knowledge graphs and machine learning models together improves system accuracy and extends the range of machine learning capabilities for better explainability and trustworthiness.
How a knowledge graph works
The core of a knowledge graph is its knowledge model, a collection of interconnected descriptions of concepts, entities, events, and relationships known as an ontology. This model provides a framework for statements or taxonomy. Each statement consists of a subject, predicate, and object (Figure 1)—known as a triple model—and each subject or object is represented only once in the context of the other subjects and their relationships. For example, in this simple sentence, "The boy kicks the ball," The boy is the subject, and kicker is the predicate because he kicks the ball, the object.
Figure1: Apple is the subject, chief executive officer is the predicate, and Tim Cook is the object.
Likewise, each statement consists of three components: nodes, edges, and labels. A node, or vertice, represents an entity, which can be anything existing in the real world, such as a person, company, or object. For instance, in this example (Figure 2), Barack Obama is the subject node, Malia and Sasha are object nodes, and the edges, or relationships, are labeled as father or sibling, respectively.
Figure 2: How the relationships between nodes can be labeled.
What makes SESAMm's knowledge graph unique?
SESAMm uses open and private datasets with custom, curated information to create our proprietary knowledge graph. As a result, the knowledge graph is a vast map connecting and integrating over 70 million related entities and their keywords, relating each organization to its brands, products, associated executives, names, nicknames, and exchange identifiers in the case of public companies from a data repository made up of more than 18 billion articles and messages and growing.
The knowledge graph is updated regularly
Entities within the knowledge graph are updated weekly and tagged to ensure we correctly track their changes. For instance, the CEO of a company today might not be its CEO tomorrow. And brands might be bought and sold, changing the parent company with each sale. So, weekly updates within the knowledge graph ensure the system is aware of these changes.
NLP-driven accuracy
At SESAMm, named entity disambiguation (NED), a natural language processing (NLP) technique, identifies named entities based on their context and usage. Text referencing "Elon," for example, could refer indirectly to Tesla through its CEO or to a university in North Carolina. Only the context allows us to differentiate, and NED considers that context when classifying entities. This method is superior to simple pattern matching, which limits the number of possible matches, requires frequent manual adjustments, and can't distinguish homophones.
SESAMm uses three other NLP tools to identify entities and create actionable insights: lemmatization, embeddings, and similarity. The lemmatization process normalizes a word into its base form (morphology) to help identify and aggregate entities. Embedding assigns the entity a numerical value to help analyze how words change meaning depending on context and understand the subtle differences between words that refer to the same concept. Similarity measures whether two words, sentences, or objects are close to one another in meaning.
SESAMm tailored its knowledge graph to find, extract, and analyze data about public or private entities, which isn't readily available from the web or standard rating firms. This unique implementation of a knowledge graph provides insights to give you an edge when researching, analyzing, and submitting recommendations to the portfolio manager or clients.
SESAMm's premiere platform, TextReveal®, allows you to leverage NLP-driven insights fully and receive high-quality results through data streams, modular API and dashboard visualization, and signals and alerts. It's perfect for many quantitative, quantamental, and ESG investment use cases.
Learn how SESAMm can support you in your investment decision-making and request a demo today.
In our recent webinar with WeeFin, "Addressing Core Challenges in ESG Data Management," CEOs Sylvain Forté and Gregoire Hug discussed both the fast-evolving ESG landscape and how managing complex data is more critical than ever.
Watch this webinar to learn how to:
Manage the lack of standardization and the inconsistency in ESG data.
Address data quality issues and missing data.
Implement a dedicated ESG data management system to balance flexibility and standardization for meaningful reports.
Fill out the form to access the webinar replay now!
Webinar Replay: Addressing Core Challenges in ESG Data Management
SESAMm, a leading provider of Big Data and Artificial Intelligence technology for investment managers, has been recognized with the Best of Show Award at Finovate Europe 2022, which took place on March 22nd and 23rd in London. The award was granted to SESAMm following a demonstration conferred by CEO and Co-founder Sylvain Forté, during which he showcased the company's marquee product TextReveal®.
"Finovate Europe represents a unique opportunity for best-in-class Fintech companies to showcase their innovations in front of leading institutions. It was great to demonstrate our product in front of an elite audience and win the Best of Show award." Said Sylvain Forté, CEO of SESAMm,"We are proud to say that this event was a big success for SESAMm, judging by the level of interest in our technology and its applications to the current ESG topic."
SESAMm is a fintech company that specializes in Big Data and Artificial Intelligence. Through its product, TextReveal®, the company provides analytics and investment signals to finance and corporate professionals by analyzing over 17 billion web articles and messages using natural language processing and machine learning. TextReveal® is a ready-to-use alternative data platform; its NLP (Natural Language Processing) powered engine provides daily sentiment and ESG data mapped to public and private companies to fuel investment strategies.
Finovate Europe, one of the most awaited annual events, sheds light on innovative fintech startups and helps them gain more recognition. It brings together over 1,000 senior finance and tech experts, including “demoers” and insightful speakers.
"We love to see companies like SESAMm join us at Finovate demonstrating their cutting-edge technologies. It really underscores our commitment to provide a platform to promote innovative startups in the financial ecosystem." Said Greg Palmer, VP of Finovate. "Congrats to the SESAMm team for winning Best of Show, it’s clear they really resonated with our audience!"
SESAMm's successful appearance at Finovate Europe once more confirms the great reception the company is getting in the industry, as just a few weeks ago, it was announced that SESAMm was the recipient of the HFM award for Best use of Artificial Intelligence.
TextReveal® Streams emphasizes SESAMm's goal to provide future investors with the accurate and necessary data to make decisions accordingly. Find out more here.
About SESAMm:
SESAMm is a leading company in alternative data and artificial intelligence, delivering global investment firms and corporates data-driven insight and investment analytics. It owns a proprietary 13 years historical data lake containing over 17 billion articles publicly sourced from more than 4 million sources (blogs, forums, social networks, etc.). This represents 10 to 100 times more information than that of our competitors.
The aerospace and defense industry is essential to global technology and transportation, playing a crucial role in maintaining international security and connectivity. However, this sector faces intense scrutiny due to its significant impact on ESG factors. Amidst challenges like safety lapses and whistleblower revelations, stakeholders are increasingly relying on advanced AI technologies to gain insights into potential controversies. Such technologies have enabled a deeper understanding of the complex ESG issues that permeate the industry, revealing not only the specific challenges faced by companies like Boeing but also providing a broader view of the sector's commitment to corporate responsibility and sustainability.
This article explores the aerospace industry and its ESG challenges, backed up by a case study of industry giant Boeing. It also explains how we used SESAMm’s AI-powered tools to detect these controversies beforehand.
Aerospace and Defense Market Mentions
The top market players in the aerospace and defense industry command 8.3% of the overall market's online mentions. This sector is increasingly scrutinized for its ESG practices amidst technological advancements and global policy shifts.
Media Sentiment in the Aerospace Industry
In this study, we ran our AI tools through our data lake to extract the major market players: Northrop Grumman, Lockheed Martin, General Dynamics, Airbus, and Boeing, with the time frame starting from 2015 to date. The data reveals a notable peak in online mentions of the market trend, mainly following Boeing’s plane crash controversies. Post-2018, we noticed a general upward trend for Airbus and Boeing, indicating their increasing dominance or recovery in the market. This trend demonstrates the shifting landscape of the aerospace industry, where competition is intense, and the share of mentions can reflect broader market movements and company-specific developments.
(*): Polarity or sentiment polarity represents a company's aggregate of positive and negative sentiment (opinions, reviews), ranging from -1 to 1. A zero score means that there is as much positive as negative sentiment. High e-reputation brands can have polarity scores of more than 0.5.
The sentiment across the aerospace market reflects the industry’s highs and lows. On one hand, there are moments of significant achievements like new contracts and technological breakthroughs that drive companies like Lockheed Martin to positive media highlights. Between 2016 and 2018, Lockheed Martin experienced a surge in positive mentions due to key contract wins and proactive company initiatives, which have contributed to maintaining its reputation and market value.
Conversely, the industry faces intense scrutiny over various controversies, notably those surrounding Boeing. The company, a dominant figure in the market, has been at the center of numerous negative headlines, giving it the lowest sentiment polarity among its peers. Issues range from serious safety lapses, such as the tragic 737 MAX crashes throughout the years, to ongoing legal challenges and whistleblower claims that overshadow its governance practices. These incidents have not only affected Boeing’s sentiment negatively but have also influenced the overall perception of the aerospace and defense sector, highlighting the industry's susceptibility to reputational risks.
Macro Themes
The aerospace sector, while essential for global connectivity, has not been without its controversies, especially concerning safety and compliance issues. Among the major players, Boeing's significant share of media mentions is primarily driven by a series of high-profile accidents, including the 737 MAX crashes in 2019, killing all passengers and another serious incident in South China in 2022. These accidents triggered a cascade of lawsuits and fines, severely impacting Boeing’s public perception and operational standing. The aftermath of these incidents also precipitated broader discussions around leadership changes, management practices, safety protocols, and accountability measures within the company.
Similarly, Airbus has faced its own challenges, with notable accidents in 2015 in France and 2016 in the Mediterranean Sea, followed by another in 2020, resulting in 97 fatalities. These incidents underline the persistent safety risks inherent in aerospace operations and the critical need for stringent oversight. Accusations of ethical and legal violations also loom large across the industry. Boeing, for example, has been embroiled in numerous investigations and lawsuits related to various accusations. Meanwhile, other industry giants like Northrop Grumman and Lockheed Martin have faced legal actions over environmental and contracting practices, such as Northrop’s involvement in residential chemical contamination and Lockheed’s settlement over accusations of overcharging the Navy. General Dynamics has also encountered legal scrutiny over employment practices and allegations of human rights and privacy violations.
These controversies highlight a complex landscape of operational, legal, and ethical challenges in the aerospace industry. Each incident not only affects the involved company but also catalyzes shifts in regulatory practices and leadership strategies, underscoring the need for robust governance and proactive risk management to uphold safety and integrity in aerospace operations.
ESG Analysis
The influence of ESG factors on public perception and internal company policies within the aerospace industry is profound. Governance issues, in particular, continue to be a critical focus as aerospace companies confront challenges related to compliance, ethical practices, and transparency. Social factors are also prominent, with labor practices and safety standards critically influencing operational and strategic decision-making. Environmental considerations are escalating in importance as the industry progresses towards more sustainable practices, driven by increasing concerns over climate change and environmental sustainability.
Northrop Grumman illustrates an aspect of ESG concerns with specific environmental risks linked to its operations. Accusations have surfaced against Northrop Grumman for its role in environmental degradation, such as pollution from manufacturing plants and involvement in contamination incidents at residential sites. These issues not only affect the company’s environmental track record but also impact its social standing and governance integrity. The company also displays some governance risks related to its total mentions volume driven by accusations of fueling false ‘Revenge Porn’ allegations against CIA whistleblower John Kiriakou as well as legal investigations driven by Northrop Grumman investors over its claims to recover their losses and class action lawsuits over claims of a breach of fiduciary duty.
The aerospace sector’s engagement with these ESG factors indicates a shift towards addressing the critical issues facing the industry. Boeing ranks first in terms of risks, with social risks having the highest share, followed by Airbus, with risks coming from social issues such as customer relations, fundamental human rights, and governance risks mainly related to its fraud, bribery, and corruption charges. This shift is not just about mitigating risks but also about harnessing opportunities to enhance corporate responsibility and ensure long-term sustainability.
Deep Dive into Boeing: ESG Risks and Public Perception
The aerospace industry has faced increasing scrutiny over its ESG practices. Among the key players, the American aerospace company Boeing has been prominently featured in media discussions, not only due to its market distinction but also because of its ESG challenges that have sparked significant controversy.
Boeing Word Cloud
This word cloud visually represents the main online topics surrounding Boeing, particularly focusing on the issues and controversies related to the 737 Max aircraft. Key terms like "737 Max," "Boeing," "safety," "death," and "FAA" are prominently displayed, indicating these as central themes in the discussion. The size of each word in the cloud signifies its frequency and importance in related discussions, with larger words being more prevalent. This visualization encapsulates a range of associated topics such as "lawsuit," "Senate hearing," and "missed inspections," highlighting the broad spectrum of regulatory, safety, and ethical issues that have dominated public and media discourse regarding Boeing.
Boeing ESG Analysis
According to TextReveal’s findings, since 2019, Boeing's ESG risks have intensified, particularly in social and governance, leading to a substantial impact on its public image and stock performance. The company's struggles with governance issues are well-documented, encompassing major safety lapses that resulted in the tragic crashes of the 737 MAX aircraft in the span of six months in Indonesia and Ethiopia. These events have not only led to a loss of life but also raised serious questions about the company's commitment to safety protocols and ethical standards.
Social risks at Boeing are also prominent, with multiple incidents involving customer relations and human capital management. Notably, the company has faced significant scrutiny regarding its response to the 737 MAX crashes, highlighting deficiencies in transparency and accountability in dealing with the fallout. The handling of these incidents resulted in widespread public distrust, significantly damaging Boeing's relationships with airlines, regulatory bodies, and the flying public. Issues such as delays in disclosing software malfunctions and the initial reluctance to ground the fleet have led to accusations of prioritizing profit over passenger safety. Furthermore, Boeing's labor practices have also come under fire. There have been multiple instances of tension with labor unions over contract negotiations, job cuts, and factory conditions, which exacerbate the social risks by affecting employee morale and productivity. These labor disputes and the perceived erosion of safety standards contribute to a challenging environment, complicating Boeing's efforts to rebuild trust and ensure operational stability.
Early Signs: Whistleblowers
We used TextReveal's analytics capabilities to track the prevalence of whistleblower mentions within the aerospace industry, with data pointing back as far as 2019. This tool has effectively highlighted ongoing concerns and patterns related to corporate governance and safety issues.
Boeing has also been facing whistleblower retaliation. High-profile cases involving whistleblowers like John Barnett, who was found dead under mysterious circumstances, and Sam Salehpour, who reported safety shortcuts and received physical threats, illustrate the perilous environment for those who challenge the status quo. These whistleblowers' stories, while distressing, shed light on a culture that may prioritize expediency over thoroughness and safety.
One of the most significant cases involved John Barnett, a former quality manager at Boeing, who raised alarms about critical safety lapses in the production of the 787 Dreamliner. Barnett claimed that faulty parts were knowingly installed on planes, potentially endangering passengers. His revelations were met with hostility and retaliation, resulting in his tragic and suspicious death, which was officially ruled as a suicide. This case has fueled widespread media coverage and public outcry, questioning the integrity of Boeing’s internal safety practices and the treatment of employees who report such critical issues.
Another well-known whistleblower, Ed Pierson, reported concerns about the 737 MAX's manufacturing process, specifically pointing to the rushed production schedules that he believed compromised safety. His testimony before congressional hearings helped to expose a "profit over safety" mentality that appeared to saturate Boeing’s management practices. Pierson’s allegations were particularly damaging as they were directly linked to the two fatal crashes of the 737 MAX, which tragically resulted in 346 deaths.
Sam Salehpour, a Boeing engineer, also came forward with allegations of manufacturing shortcuts that compromised the structural integrity and safety of Boeing aircraft. Like others, Salehpour faced significant backlash from superiors and was reportedly blackballed within the industry for his outspokenness, highlighting the severe personal and professional risks faced by whistleblowers within the air travel giant.
The cumulative effect of these whistleblower cases has led to significant scrutiny from regulatory bodies, the media, and the public. The Federal Aviation Administration (FAA) has stepped up its oversight of Boeing, leading to fines, increased regulations, and a temporary grounding of the 737 MAX fleet. These incidents have sparked broader discussions about the need for systemic reforms within the aerospace industry to ensure that safety and ethical standards are not only upheld but prioritized over financial incentives.
How does SESAMm Detect ESG
Navigating the vast amounts of data available is a significant challenge when conducting this type of analysis. At SESAMm, our experts begin with a comprehensive sentiment analysis of the industry and its key players. By examining trends, particularly spikes in data volume or shifts in sentiment—both positive and negative—they can pinpoint the issues and controversies driving these changes. Following this, our team conducts a thematic deep dive into the topics most relevant to the industry, providing a nuanced understanding of the issues that are particularly sensitive for stakeholders. With these insights in hand, our team then moves to company-specific analyses and benchmarking to assess how individual companies perform relative to their peers.
SESAMm's TextReveal® platform plays a significant role in identifying and understanding the complex web of controversies within industries such as aerospace. Through its algorithms, the platform sifts through vast amounts of data from diverse sources like news outlets, social media, and corporate disclosures to detect subtle cues and patterns that might indicate emerging ESG controversies. This robust data collection and analysis enable SESAMm to pinpoint issues related to whistleblower activities, safety violations, and governance lapses well before they gain widespread attention. By integrating this intelligence, SESAMm facilitates a deeper understanding of the underlying factors contributing to these controversies, aiding stakeholders in navigating the intricate dynamics of corporate accountability and regulatory compliance.
SESAMm's TextReveal® platform provides a comprehensive suite of ESG analytics tools that leverage extensive data collection from news outlets, social media, corporate disclosures, and NGO reports, ensuring thorough coverage of emerging and underreported ESG issues. Utilizing advanced artificial intelligence, the platform analyzes sentiments and contextual nuances within this data to identify positive and negative ESG indicators, helps stakeholders measure public sentiment before issues escalate, and makes accurate business decisions. Additionally, its capability to identify and map relationships between entities such as companies, individuals, and products to various ESG issues is crucial for assessing how internal dynamics influence a company’s overall ESG profile.
TextReveal® also employs predictive analytics to foresee potentil ESG controversies, enabling proactive risk management and strategic planning. Moreover, it offers detailed ESG reporting and scoring, providing quantifiable insights into a company’s ESG performance, which is invaluable for investors and analysts. Lastly, the platform’s analysis of the influence of key individuals on ESG practices offers deeper insights into leadership effectiveness and ethical compliance, making SESAMm's tools essential for integrating ESG considerations into comprehensive corporate strategy and maintaining competitive advantage in a socially conscious market environment.
Conclusion
Navigating the complexities of ESG risk management requires a shift from traditional methods to more advanced, AI-driven approaches. AI's ability to analyze vast amounts of unstructured data enables early detection of hidden risks, as demonstrated in our case study on Boeing. Using AI, we identified emerging controversies around Boeing's safety practices, quality control, and governance issues before they escalated, showcasing the technology's potential for proactive risk management.
Incorporating AI into ESG assessments allows private equity firms and other stakeholders to move beyond reactive strategies. By detecting potential risks early, firms can safeguard their investments, protect their reputations, and align with a growing emphasis on responsible investing. Embracing AI-driven tools is not just about keeping pace with market demands—it's about ensuring a more secure, transparent, and sustainable approach to investment in an ESG-focused world.
Reach out to SESAMm
TextReveal’s web data analysis of over five million public and private companies is essential for keeping tabs on ESG investment risks. To learn more about how you can analyze web data or to request a demo, reach out to one of our representatives.
Stay ahead with the latest in ESG and AI intelligence
Join our mailing list to receive new reports, event invites, and updates from SESAMm directly to your inbox.