• Member Login
  • Contact
  • Resources

Lost your password?

  • English English English en
  • العربية العربية Arabic ar
  • Indonesia Indonesia Indonesian id
  • Melayu Melayu Malay ms
  • Български Български Bulgarian bg
  • hrvatski hrvatski Croatian hr
  • Čeština Čeština Czech cs
  • Dansk Dansk Danish da
  • Suomi Suomi Finnish fi
  • Français Français French fr
  • Deutsch Deutsch German de
  • Ελληνικά Ελληνικά Greek el
  • हिन्दी हिन्दी Hindi hi
  • Italiano Italiano Italian it
  • 简体中文 简体中文 Chinese (Simplified) zh-hans
  • Norsk bokmål Norsk bokmål Norwegian Bokmål no
  • Română Română Romanian ro
  • Русский Русский Russian ru
  • српски српски Serbian sr
  • Slovenčina Slovenčina Slovak sk
  • Slovenščina Slovenščina Slovenian sl
  • Español Español Spanish es
  • Svenska Svenska Swedish sv
  • Tagalog Filipino Tagalog Filipino Tagalog Filipino tgl
  • Tamil Tamil Tamil ta
  • ไทย ไทย Thai th
  • Türkçe Türkçe Turkish tr
  • اردو اردو Urdu ur
  • Tiếng Việt Tiếng Việt Vietnamese vi
  • 日本語 日本語 Japanese ja
AMEC
Search Search

International association for the measurement and evaluation of communication

  • Education
    • AMEC Online College
      • AMEC Training Opportunities
      • AMEC Academic Scholarship (SAREC)
      • AMEC Certificate in Measurement & Evaluation
        • FAQs – AMEC Certificate Course
        • AMEC Certificate Alumni
        • Student Testimonials
        • AMEC IEF Tutorial Course
        • Diploma – Coming 2025
      • AMEC Foundation in Measurement & Evaluation
        • FAQ’s – AMEC Foundation Course
      • AMEC Academic Advisory Group
      • AMEC Student of the Year Awards
      • AMEC Academics and Educators Special Interest Group (SIG)
  • Resources
    • Integrated Evaluation Framework (IEF)
      • AMEC IEF Tutorial
    • Barcelona Principles 3.0
    • Measurement Maturity Mapper – M3
    • Say No to AVEs
    • GDQ Data Quality Excellence Pledge
    • MEL Manual for Public Communications
    • Videos
    • Case Studies
    • AMEC Innovation Hub Series
    • 2023 AMEC Agency White Paper
    • AMEC Planning Resources
    • Measurement Methodology
    • 2023 AMEC APAC Market Insights Paper
    • AMEC Measurement Month
    • Find a Speaker
  • Events
    • Events Calendar
      • Events & Webinars
      • Chatham House Rules
    • Measurement Month
      • 2024 Events
      • 2023 Events
      • 2022 Events
      • All Events
    • Summits
      • All Summits
      • 2025 Global Summit – Vienna
      • 2024 Global Summit – Sofia
      • 2023 Global Summit – Miami
      • 2023 Regional Summit – Jakarta
      • 2022 Global Summit – Vienna
      • 2021 Global Summit – Virtual
      • 2020 Global Summit – Virtual
      • 2019 Global Summit – Prague
      • 2018 Global Summit – Barcelona
      • 2017 Global Summit – Bangkok
    • 2025 AMEC Global Communication Effectiveness Awards
      • 2025 Awards
      • 2024 Awards Winners
      • 2024 Awards
      • 2023 Awards Winners
      • 2023 Awards
      • 2022 Awards Winners
      • 2022 Awards
      • 2021 Awards Winners
      • 2021 Awards
      • Past Award Winners
      • Don Bartholomew Award Winners
  • About
    • Who We Are
      • About AMEC
      • AMEC Board of Directors
      • AMEC Special Interest Groups
      • Partners & Alliances
      • AMEC Don Bartholomew Award Winners
    • Chapters
      • Asia Pacific Chapter
      • European Chapter
      • Latin America Chapter
      • Middle East and Africa Chapter
      • North American Chapter
  • Insights
  • Membership
    • Join AMEC
      • AMEC Special Interest Groups
      • AMEC Global Chapters
      • Membership Categories
      • Member News Sign-Up
    • Membership Directory
      • See all Members
    • AMEC Board Elections
      • AMEC AGM 2024
      • AMEC Elections 2024
      • AMEC Elections 2023 Results
      • AMEC AGM 2022
      • AMEC Elections 2022 Results
      • AMEC AGM 2021
      • AMEC Elections 2021 Results
      • AMEC AGM 2020
      • AMEC Elections 2020 Results
      • AMEC Elections 2019 Results
    • Exclusive for Members
      • Member News Sign-Up
      • AMEC General Webinars (members only on-demand)
      • AMEC NFP SIG “Ask the Experts” Series
      • All Measurement Month Events
      • AMEC Agency Toolkit Series
      • AMEC North America Chapter “Ask the Experts” Series
      • AMEC European Chapter – Hints and Tips
      • AMEC Global Membership Survey
  • Resources
  • Menu Menu

Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation: an introduction

You are here: Home » AMEC Member Article » Innovation Hub » Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation:...
Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation: an introduction_Konstantinos Karakostas_Director of Machine Learning_Commetric

Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation: an introduction

27th April 2023/in AMEC Member Article, Innovation Hub, News Commetric, Konstantinos Karakostas, PhD/by Julie Wilkinson

by Konstantinos Karakostas, PhD – Director of Machine Learning, Commetric

Amid all the hype around ChatGPT, Bing Chat, Google Bard and other fascinating user-facing tools launched, we are all reading more and more stories online about the potential impact of generative artificial intelligence. Generative AI has the potential to transform the way we live and work, but it is important to understand its limitations and use it responsibly. This technology also presents a compelling opportunity for the communication measurement and evaluation industry to become more efficient and productive. Let us now look into some key concepts.

The lay of the land

Generative AI refers to the ability of Artificial Intelligence to generate content that is new and original, based on the input it receives. This is in contrast to traditional AI, which operates based on specific instructions and algorithms. Generative AI can produce a wide variety of content, including text, images, and videos, that can be used for a variety of applications, such as content creation, product design, and even medical research. One of the key features of generative AI is its ability to learn from large amounts of unstructured data and use this knowledge to generate new content.

Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation: an introduction

Images created by DALL-E 2 with prompt “Analyst aided by AI tools processing media coverage”

Generative AI is based on large language models (LLMs), which are trained on massive amounts of text data for natural language processing (NLP) tasks. The latest approach in LLMs is based on a neural network architecture, coined ‘Transformers,’ which combines transformer architecture with unsupervised learning to develop large foundation models. These foundation models serve as the starting point for the development of more specialised and sophisticated models that can be tailored to specific use cases or domains.

Know the limits

While generative AI presents a compelling opportunity to augment human efforts and make enterprises more productive, it is important to understand its limitations. One of the key limitations is the cost to train and maintain foundation models, which can be expensive for smaller enterprises to undertake on their own. Additionally, these models may not always be trustworthy, as they are often trained on large amounts of unstructured data, some of which may be biased or contain toxic information.

It is also important to note that generative AI is not a one-size-fits-all solution. Choosing the correct LLM to use for a specific job requires expertise in LLMs. For example, Google’s BERT is designed to understand bidirectional relationships between words in a sentence and is primarily used for task classification, question answering, and named entity recognition. On the other hand, GPT is a unidirectional transformer-based model primarily used for text generation tasks such as language translation, summarisation, and content creation.

In general, LLMs can generate coherent and complex text that resembles human writing, such as news articles, poetry, or even entire books. They can also perform language-related tasks such as language translation, summarisation, and answering questions based on text. However, LLMs still struggle with understanding the context, sarcasm, and humour in language and can produce biased or inaccurate results when trained on biased or inaccurate data. Additionally, they are not capable of understanding emotions, reasoning, or making ethical judgments.

PR’s AI revolution?

LLMs are already showing great promise for the PR measurement and media analytics industry, with their ability to quickly and accurately analyse large amounts of text data. One of the main benefits of LLMs is that they can easily identify patterns and trends in almost any language, providing valuable insights into how media are reporting or how users on social media are talking about a brand, product, or service.

In the world of media analytics, LLMs are being used to track and analyse mentions of a brand across various media channels, including social media, news articles, and online forums. By understanding the sentiment and tone of these mentions, brands can gain valuable insights into how their products or services are interpreted by media stakeholders or target audiences.

LLMs are also being used to measure PR campaigns effectiveness – for instance in terms of achieving message pull-through. By analysing the language used in media coverage, LLMs can provide insights into messaging effectiveness and help identify areas for improvement.

However, it is important to note that LLMs are not a replacement for human analysis and interpretation. While they can quickly and accurately analyse large amounts of text data, they lack the ability to understand the nuances of language and context that a human analyst can provide, and would also lack the background needed to understand clients and tailor insights to their communication objectives.

Overall, generative AI and LLMs are a powerful tool for PR measurement and media analytics. They have the potential to transform the way we work, but it is important to understand their limitations and use them responsibly – particularly when integrating generative AI output to client-facing platforms or reports. We as a professional community need to understand how we can make the best use of generative AI technologies and how we can participate in and shape important conversations around ethics and compliance in relation to generative AI.

About Konstantinos Karakostas, PhD – Director of Machine Learning, Commetric

Kostas has been working in media evaluation and digital marketing, leading a team of Data Scientists, designing developing and deploying AI solutions for NLP/NLU projects including polarity, emotion detection, thematic classification, topic detection, aspect extraction and demographic & psychographic profiling.

He has previously worked as High Energy Physicist and Data Scientist on terascale level for CERN, the European Organisation for Nuclear Research based in Geneva.

A research enthusiast and academician, Kostas has been a research associate and a lecturer in Technical University Athens and LAPP in France (Laboratoire d’Annecy De Physique Des Particules).

Kostas holds a PhD in Experimental Particle Physics & Data Science from CERN and a Masters Degree in Applied Physics from Technical University Athens.

This is article is part of The Innovation Hub Series

Tags: AI, Communication, Generative LLM, Measurement, PR
Share this entry
  • Share on Facebook
  • Share on X
  • Share on LinkedIn
  • Share by Mail
https://amecorg.com/wp-content/uploads/2023/04/AMEC-website-1-1.jpg 451 1200 Julie Wilkinson https://amecorg.com/wp-content/uploads/2019/09/Large-amec-logo-master-1024x232.png Julie Wilkinson2023-04-27 14:06:152023-05-10 11:26:18Leveraging Generative AI and LLMs for PR and Comms Measurement and Evaluation: an introduction

News and Spotlights

News

Pledge Support for the Global Data Quality Intiative

10th March 2025

News

The Power Trio: How Sales, Finance, and Marketing Rescue PR from the ROI Dilemma

12th February 2025

See more News Stories
View Measurement Month Events
Visit the AMEC Resource Centre
Amec News

Keep up to date with the latest news and trends



By clicking Submit, you have read and agreed to receive emails from AMEC. You can find more in our Privacy Policy.

Connect with AMEC

Quick Resources

  • M3- Measurement Maturity Mapper
  • Integrated Evaluation Framework
  • GDQ Data Quality Excellence Pledge
  • PR’s Guide to Measurement
  • Events Calendar
  • Measurement Month
  • Speakers Bureau
  • Resources

Member Areas

  • AMEC Global Membership Survey
  • Membership Directory
  • Exclusive for Members
  • Privacy Policy Terms and Conditions
  • Sitemap
  • Resources
Copyright © 2025 AMEC. All Rights Reserved. All Trademarks Acknowledged. - Website by Blaze Concepts
Link to: AMEC Welcomes New Member GRF+ Link to: AMEC Welcomes New Member GRF+ AMEC Welcomes New Member GRF+AMEC Welcomes New Member GRF+ Link to: Innovation Hub Series: AMEC presents Link to: Innovation Hub Series: AMEC presents The Innovation Hub Series_AMEC Insights blogInnovation Hub Series: AMEC presents
Scroll to top Scroll to top Scroll to top