Category Archives: Application Areas of Text Analytics

Posts about Application Areas of NLP / Natural Language Processing / Text Analytics

Corporate Reputation Analysis at Scale

The rationale for Corporate Reputation Analysis Automation

Reputation

We live in an age where news stories are no longer a primary, but an added concern for businesses trying to build and maintain a strong reputation. Individual experiences are reaching a global audience in a matter of minutes, thanks to the internet, which has made way for an immense volume of spontaneous and real-time information. There is no doubt that companies have to navigate the voices of traditional and contemporary media sources, both of whom contribute significantly to their social standing. Reputation crises can spark at any moment, and traditional reputational audits can not help to mitigate them. Consequently, it is more important than ever before to keep track of reputation in real-time.

The MeaningCloud Corporate Reputation Analysis API is a new service that enables companies to take advantage of social networking platforms, forums, blogs, surveys, and news sources in a bid to do just that. While we have been running a service in this field since 2011, our new API employs a distinct approach to tackle the task of Corporate Reputation analysis.

Reputation management fundamentals

The MeaningCloud Reputation API uses a categorization scheme based on the work by Charles Fombrun and Cees van Riel. In 1999, they founded The Reputation Institute (now, The RepTrak Company™), the world’s leading reputation data and insights company. In collaboration with Harris Interactive, The Reputation Institute developed Reputation Quotient (RQ) in 1999, replaced in 2005 by the RepTrak® model.

The RepTrak Company™ has become highly esteemed on a global scale for its publication of reports on corporations’ reputation (as well as countries and cities). Furthermore, it has developed models that have provided companies with the autonomy to qualify their reputation in a meaningful way. It is important to note that other well-known frameworks do exist. The MERCO Indexes, for instance, are particularly renowned in Spain, Portugal, Italy, and across Latin America for their “multi-stakeholder methodology, composed of six evaluations and more than twenty information sources”. MERCO has been analyzing reputation since the year 2000.

To analyze Corporate Reputation in a piece of text, we follow the seven dimensions proposed in the foundational work of this field, globally considered to be the most important drivers of reputation:

  1. Citizenship:
    Both a company that actively strives and one who is idle in their efforts to be environmentally responsible, ensuring they support good causes and positively influence society, are equally susceptible to a change in their reputational outlook.
  2. Governance:
    A company needs to be open and transparent, ethical and fair in order to boost its reputation.
  3. Innovation:
    Innovative companies are market leaders and adapt quickly to change generally have a better social standing.
  4. Leadership:
    Suppose a company has inspiring/motivating leaders who display personal integrity, competence and knowledge, effective communication, and a clear vision for the future. They are likely to have a positive effect on the company’s repute.
  5. Performance:
    A measure of determining how profitable a company is, whether they exceed expectations and have solid prospects for the future. All of which are qualities of a reputable company.
  6. Products and Services:
    High-quality products/services that meet customer needs and are fully backed by the company undoubtedly contribute to a company’s social status.
  7. Workplace:
    A company must reward employees fairly, show genuine concern for them, and respect diversity to maintain a good reputation.

Our new Corporate Reputation API

The MeaningCloudReputation API is now available in 57 languages. The core processing is carried out in English. For other languages, the source text is translated first with the MeaningCloud Machine Translation API. For example, a user can throw an API request with a text in German. He/she can specify the source language (if known) as a parameter in the call or select “autodetect” to let our algorithms discover the source language, translate it into English (if needed), and carry out the reputation analysis on the translated text.

The MeaningCloud Corporate Reputation API goes beyond the automatic discovery of a mention related to a particular dimension in a Corporate Reputation model:

  1. It first detects the language of the text under analysis and translates it into English if needed.
  2. It disambiguates the mentions of entities in the text. Users can extend the (vast) resources updated daily in the platform with new companies via user dictionaries.
  3. It discriminates the reputation dimensions evoked in the text.
  4. It analyzes each dimension’s polarity (positive, negative, neutral, or non-existent) in a reputational context.
  5. It attaches the pair dimension/polarity to one of the entities mentioned in the text or to a declared default entity.

Reputation Management

Tools for PR, communication, marketing, and social listening companies

MeaningCloud is just a tech company specialized in Natural Language Processing. We do not collect information over the internet to assess the reputation of companies. Instead, we build the technology that permits third parties to develop and leverage NLP technology to provide actionable insights into:

  • The overall perception of the company.
  • The impact that news and social media content have on the company’s reputation.
  • The areas of the company requiring special attention.
  • The areas of the company making a good impression.
  • Third companies that are mentioned jointly and how their respective reputations compare.

The limits of the technology

As always with NLP solutions, and despite our continuous efforts, this API cannot be entirely free from errors or biases coming from different sources:

  • Our interpretation of the dimensions of reputation, that we know through the widely available literature on this subject.
  • Limitations in our algorithms for linguistic analysis and translation models.
  • Lack of adaptation to a particular domain or industry. Our general-purpose API can be improved to interpret reputational aspects more precisely when analyzing companies in a particular industry: utilities, finance, retail, telecom, healthcare, etc.

Our Corporate Reputation API derives from:

  • Our experience in customer feedback analysis, using the same basis as our Voice of the Customer analysis models.
  • The version of the API for Spanish, which has been public since 2012 (at textalytics.com until 2015 and at meaningcloud.com since then.)

Free Corporate Reputation Analysis

Our API is now published in beta version. For now, the pricing is the same as for other premium APIs: one request (or credit) is charged per 125 words or fraction. Two credits if translation is required. However, temporarily, there is no need to pay a flat fee for usage, as is the case for our Voice of the Customer/Employee APIs.

Follow this link to learn more about our Corporate Reputation API.

Furthermore, remember that you can test the API extensively, analyzing up to 20,000 texts for free per month, just by registering at meaningcloud.com.

Disclaimer

To be completely transparent about our credentials, we have to make it clear that:

Corporate Reputation ReviewReferences

An excellent source of information about this field is the journal Corporate Reputation Review. Launched in 1997, it publishes empirical and conceptual research on reputation management and closely related fields, such as strategic/corporate communication, corporate social responsibility (CSR) communication, corporate identity, and organizational identity.

Fombrun, C. and Shanley, M., 1990. What’s in a name? Reputation building and corporate strategy. Academy of management Journal, 33(2), pp.233-258.

Fombrun, C. and Van Riel, C., 1997. The reputational landscape. Corporate reputation review, pp.1-16.

Fombrun, C.J., Gardberg, N.A. and Sever, J.M., 2000. The Reputation Quotient SM: A multi-stakeholder measure of corporate reputation. Journal of brand management, 7(4), pp.241-255.

Fombrun, C.J., Van Riel, C.B. and Van Riel, C., 2004. Fame & fortune: How successful companies build winning reputations. FT press.

Ponzi, L.J., Fombrun, C.J. and Gardberg, N.A., 2011. RepTrak™ pulse: Conceptualizing and validating a short-form measure of corporate reputation. Corporate reputation review, 14(1), pp.15-35.

Fombrun, C.J., Ponzi, L.J. and Newburry, W., 2015. Stakeholder tracking and analysis: The RepTrak® system for measuring corporate reputation. Corporate reputation review, 18(1), pp.3-24.

Pallarés Renau, M. y López Font, L., 2017. Merco y RepTrak Pulse: Comparación cualitativa de atributos, variables y públicos, Icono 14, volumen 15 (2), pp. 190-219.

 

Janine Garcia, Nadine Shallow, Maria Jose Garcia, Concepcion Polo, and Jose Gonzalez


Full IAB taxonomy for content classification now available

The surge of content marketing, based on the creation and distribution of valuable content, is a reality. The objective is no longer solely to advertise but to engage and offer valuable experiences to the market as well. In this context, precision in content classification is becoming essential. And that’s why we implemented a new automatic content classifier according to the full IAB taxonomy.

Therefore, since including tier 3 of the content taxonomy to the categorization categories of our IAB model last year, we have chosen to complement it by providing the complete ontology. In line with the Content Taxonomy, published in 2017 and updated in 2020 by the IAB Tech Lab (Interactive Advertising Bureau), this classification includes the remaining 60 categories that make up tier 4.  A total categorization of over 698 categories, hierarchized into four tiers, is thus, offered. We have kept the unique identifier that IAB assigns to each one of its categories, as well as their name, through which its parent categories can be found.

Continue reading


A Quick Introduction to Brand Monitoring and Brand Protection

[EDITOR’S NOTE: This is a guest post by David Bitton, Product Manager at Webhose.io]

Organizations should never underestimate the power of their brand. What starts out as a name, logo, vision, mission statement, website, and perhaps a few employees start to form an organization’s identity. As an organization grows, all of these key parts evolve over time to help customers identify the brand.

But a brand is more than its identity. A brand should evoke emotion from its customers – ideally a positive one – creating brand loyalty and repeat purchases of its goods or products. Loyal customers also refer the brand to friends, family, and acquaintances.

In today’s digital age, building and maintaining a strong brand is so important that brand monitoring plays a crucial role in organizations’ marketing strategy. However, with the rise of the dark web, brand monitoring has evolved to now include Digital Risk Protection. DRP protects the brand’s digital assets from various malicious actors intent on causing the brand and its reputation significant damage.

Continue reading


Accuracy measures in Sentiment Analysis: the Precision of MeaningCloud’s Technology

Accuracy Measures of Commercial Sentiment Analysis APIs

Our clients frequently ask, “what’s the precision of MeaningCloud technology?” How does it compare with other commercial competitors and with state-of-the-art technology? And they demand precise numbers.

That’s not an easy question to answer. Even when there are milliards of research studies on this issue. For the sake of simplicity, let’s concentrate on the well-studied scenario of accuracy measures in Sentiment Analysis. Continue reading


IAB Taxonomy Level 3 now available in our Deep Categorization API

IAB - Interactive Advertising BureauDigital marketing is becoming a fundamental pillar, by leaps and bounds, in the business plans of practically every business model. Methods are being refined and the search for the connection between brand and user is expected to become increasingly more precise: a related advertisement is no longer sufficient, now the advertisement must appear at the right time and in the right place. This is where categorization proves to be an exceedingly useful tool.

That is why, at MeaningCloud, we have improved our IAB categorization model in English, that is integrated in our Deep Categorization API:

  • Adding a third level of content taxonomy to the hierarchy of categories (IAB Taxonomy Level 3).
  • Improving the precision of pre-existing categories.
  • Including the unique identifiers defined by IAB itself for each of the categories.

Continue reading


Use of Text Analytics in Marketing Research

With this post, we start a series dedicated to the use of our Text Analytics technology in the field of R&D in different sectors. This post is dedicated to the use of Text Analytics in Marketing Research.  First of all, we would like to thank the researchers who have selected our services (within a wide range of competitors) as a basis for their research or innovation projects.

Marketing Research

The applications of Text Analytics in marketing are countless. That is why more and more companies are using these tools, starting with giants like Nielsen or TNS. Text analysis driven by natural language processing (NLP) is helping to transform digital marketing strategies. There are several uses for it in the company: evaluating marketing impact, optimizing customer service and SEO, making the most of influencer marketing, and significantly improving social listening. We will elaborate on this last topic in a future post.

Continue reading


Scale and optimize your Market Intelligence processes with text analytics

Competing in the 21st century requires a 360º vision of our markets (customers, competitors, suppliers, technologies, regulation). Market Intelligence is becoming increasingly important; but, its dependence on manual processes, that are not very scalable, renders its application in decision making difficult. Deep text analytics allows for more scalable and actionable Market Intelligence.

Market Intelligence: benefits and limitations

Market Intelligence consists of collecting information about a certain market in a broad sense (i.e. its customers, competitors, partners and supply chain, investors, economic, legal and technological environment…) to extract actionable insights that can be used for strategic decision-making.

Continue reading


Recorded webinar: Deep Text Analytics for More Scalable and Valuable Market Intelligence

Thank you for your interest in our webinar “Use Deep Text Analytics to Achieve More Scalable and Valuable Market Intelligence” held on June 23rd.

We explained how deep text analytics automatically understand detailed Market Intelligence information and enable applications that enable you to identify business opportunities and capture value from your market much more effectively.

In the session we covered these items:

  • Introduction to Market Intelligence
    • Benefits and limitations
  • Applying deep text analytics
    • Integrating multiple sources
    • Discovering business opportunities
    • Understanding our customers in depth
    • Analyzing the environment
    • Detecting signs of growth

Interested? Here you have the presentation and the recording of the webinar.

(También presentamos este webinar en español. Tenéis la grabación aquí.)

Continue reading


Leverage Text Analytics to Boost your Market Intelligence (webinar)

Market Intelligence and Competitive Intelligence are essential for the survival and progress of companies. Nevertheless, to perform them with the essential quality- and speed-requirements  involves analyzing an extreme volume and variety of information sources: social comments, news, legislation, scientific articles, patents and various external websites.

Market IntelligenceIn many cases this requires a handcrafted process of manually reviewing content to extract the elements of information that really serve to make strategic decisions. A process that does not scale, is inefficient and expensive.

Deep text analysis allows us to optimize and accelerate the process, not only by detecting mentions of companies or brands and categorizing content thematically, but also by automatically extracting meaningful sematic relationships between topics, discovering new emerging issues and summarizing documents to make the use of that wealth of content faster and more efficient.

Continue reading


Obtain deep customer insights with MeaningCloud

Companies need to analyze the feedback that customers provide to them through a variety of unstructured channels: surveys, interviews, contact center, social media. However, the text analytics solutions available are limited to a shallow analysis of the feedback. In this post we show you how to use deep analytics to get a complete picture of customer opinions, perceptions, emotions and intentions.

Companies need to become customer-focused in order to understand the needs and opinions of their customers and thus, define the proverbial “segment of 1”. This forces us to implement Voice of Customer (VoC) analysis initiatives that go far beyond the typical periodic satisfaction survey with numerical scores, to look for new sources of insights.

Continue reading