Latest news with #sentimentanalysis
Geeky Gadgets
3 days ago
- Business
- Geeky Gadgets
LangExtract : Google's New Library for Simplifying Language Processing Tasks (NLP)
What if you could simplify the complexities of natural language processing (NLP) without sacrificing accuracy or efficiency? For years, developers and researchers have wrestled with the steep learning curves and resource-intensive demands of traditional NLP tools. Enter Google's LangExtract—a new library that promises to redefine how we approach tasks like information extraction, sentiment analysis, and text classification. By using the power of large language models (LLMs) such as Gemini, LangExtract offers a streamlined, accessible, and highly adaptable solution to some of NLP's most persistent challenges. Whether you're a seasoned professional or a curious newcomer, this tool is poised to transform how we interact with language data. In this overview Sam Witteveen explores how LangExtract is reshaping the NLP landscape with its focus on efficiency and user-centric design. From its ability to process long-context data to its reliance on few-shot learning, LangExtract eliminates the need for extensive datasets and computational resources, making it a fantastic option for industries like finance, healthcare, and legal services. But what truly sets it apart? Is it the seamless integration into existing workflows, the reduced operational overhead, or the promise of high-quality results with minimal effort? As we unpack its features and applications, you'll discover why LangExtract is more than just another library—it's a bold step toward providing widespread access to advanced NLP capabilities. Overview of LangExtract Features How LangExtract Compares to Traditional NLP Tools Traditional NLP tools, such as those based on BERT, often require substantial fine-tuning, large datasets, and significant computational resources to achieve optimal performance. LangExtract eliminates much of this complexity by using the power of LLMs. With just a few well-crafted examples and prompts, users can achieve reliable and accurate results without the need for extensive training or resource-intensive processes. This makes LangExtract particularly appealing for production environments where time, cost, and efficiency are critical factors. Additionally, LangExtract's ability to process long-context data and generate structured outputs in formats like JSON ensures seamless integration into existing workflows. This flexibility allows users to experiment with different LLM versions, balancing performance and cost to meet specific project requirements. Google's New Library for NLP Tasks : LangExtract Watch this video on YouTube. Take a look at other insightful guides from our broad collection that might capture your interest in language processing. Practical Applications Across Industries The versatility of LangExtract makes it suitable for a wide range of real-world applications, including: Metadata Extraction: Processes large text corpora, such as news articles, legal documents, or financial reports, to extract valuable metadata efficiently. Processes large text corpora, such as news articles, legal documents, or financial reports, to extract valuable metadata efficiently. Training Dataset Creation: Assists the creation of specialized datasets for smaller models with minimal manual effort. Assists the creation of specialized datasets for smaller models with minimal manual effort. Automated Data Labeling: Streamlines the data labeling process, making it faster and more efficient for production environments. Its ability to handle extensive datasets and deliver accurate, structured outputs makes LangExtract an indispensable tool for industries that rely on precise and efficient information extraction, such as finance, healthcare, and legal services. Accessible and User-Friendly Design LangExtract prioritizes ease of use, offering a straightforward setup process that integrates seamlessly into existing workflows. By using widely used Python libraries and API keys, users can quickly implement LangExtract without requiring extensive technical expertise. Built-in visualization tools further enhance its usability, allowing users to analyze extracted data and refine their processes effectively. This focus on accessibility lowers the barrier to entry, making advanced NLP technologies available to a broader audience, including businesses, developers, and researchers. Whether you are a seasoned professional or new to NLP, LangExtract provides a practical and efficient solution for tackling complex language processing tasks. Advantages Over Conventional NLP Approaches LangExtract offers several distinct advantages compared to traditional NLP tools: Reduced Data Requirements: Eliminates the need for extensive data collection and model training, saving time and resources. Eliminates the need for extensive data collection and model training, saving time and resources. Operational Efficiency: Uses LLMs as a service, significantly reducing computational and resource overhead. Uses LLMs as a service, significantly reducing computational and resource overhead. User-Centric Design: Provides a polished and intuitive alternative to libraries like Prodigy and SpaCy, focusing on simplicity, scalability, and ease of use. By emphasizing efficiency, scalability, and user-friendliness, LangExtract enables users to achieve high-quality results with minimal effort. This makes it an ideal choice for both large-scale enterprise applications and specialized NLP projects. Media Credit: Sam Witteveen Filed Under: AI, Top News Latest Geeky Gadgets Deals Disclosure: Some of our articles include affiliate links. If you buy something through one of these links, Geeky Gadgets may earn an affiliate commission. Learn about our Disclosure Policy.
Forbes
21-07-2025
- Business
- Forbes
The 2025 AI Landscape: What Communicators Need To Know Now
Mark Dollins, President—North Star Communications Consulting and adjunct professor, University of Missouri School of Journalism. Let's face it, employee communicators: Our heads are spinning with AI. Read this, watch that, check out some new app. It seems like every time we feel we have our heads wrapped around what to do with AI, there's a new piece of research—a cool, new 'shiny thing' or application upgrade we should know, see and use. I know every time I see a new AI-driven app, I get an uneasy feeling, wondering how many other tools I might be missing that could make my work more efficient or help my clients do the same. A Digestible Look At What Matters In AI So how can we digest volumes of insights, data, trends and case studies about AI and employee communications in a weekend read? That's what our '2025 AI Landscape for Employee Communications' report is designed to do. For each of the past three years, we've combed through new AI apps, academic research and mainstream media reports to pull together a holistic view of AI through the lens of the employee communicator. Not surprisingly, our story continues to evolve; between 2023 and 2025, our global community has moved from resistance and mild curiosity to fully embracing and applying AI for productivity and creativity; in 2025, in particular, it is moving into more strategic applications. The Shift Toward Strategy And Sentiment I'm seeing far greater use of AI for sentiment analysis, and in analyzing employee feedback data from global CEO town halls. That, in turn, is driving more real-time adjustments in messaging refinement and internal communication strategies. The report goes beyond the numbers presented in this year's global survey results and connects them to broader trends, insights, case studies and recommended actions. The most surprising—and encouraging—trends show that communicators are increasingly warming up to the need to learn about and engage with machine learning as part of their competency development. There's also a deep understanding of the importance of applying change management discipline when rolling out AI technologies internally, along with the corresponding need for clear change management communications. From Skepticism To Strategic Adoption Initially met with skepticism and fear in 2023, AI now plays a significant role in enhancing productivity, creativity and strategic decision-making within employee communication functions. This year, 70% of communicators report they are using AI tools. Its greatest current value remains in improving efficiency and saving time in drafting materials, researching content and generating ideas. Personally, it's saving me two to three hours weekly in baseline research and content drafting, but I still need to pay close attention to accuracy, and validate everything ChatGPT produces. Prompt writing is one area in particular that I've focused on upskilling. I've learned that the more detail I provide early in prompt writing, the closer and faster I get to a solution that's workable. I've also learned the importance of asking ChatGPT to ask me 10 to 15 questions up front, even before I write the first version of a prompt. This helps me ensure I'm thinking holistically about what I want and what ChatGPT needs to deliver an optimal answer faster. In terms of strategy, AI is increasingly being used for data analysis, trend identification and predictive analytics—intended outcomes that require deeper collaboration with professionals outside of traditional communication roles. The ability to work with machine learning and deep learning technologies is necessary for communicators to make data-driven decisions that enhance engagement and communication effectiveness. I reached out to a machine learning engineer to learn what I didn't know about machine learning, and it was a lot. I recommend that every communicator take an IT partner in their organization to breakfast or lunch to do the same. Great partnerships start with the simplest actions. Leadership, Training And The Case For Governance Leadership's role in AI adoption remains crucial, with communication leaders—especially those leading employee communications—needing to lead AI strategy and policy development. However, many organizations still lack formal training programs, leaving employees to develop AI skills independently. I believe formal training on AI issues attached to governance and compliance is critical for the enterprise, but that individual learning for job- or function-specific benefits should be individually focused. Under any scenario, leadership should incorporate it into change management and employee communication strategies. Ethical concerns about AI, particularly in relation to bias, privacy and data protection, have become prominent. Communicators are increasingly tasked with ensuring that AI systems operate fairly and transparently, and they must be proactive in addressing concerns around accuracy, security and the ethical implications of AI use. An AI governance committee, with representation from IT, legal, HR and communications, is a good place to start. In fact, AI governance frameworks should establish clear policies and ensure AI tools are used in ways that align with company values and culture. As AI tools become more integrated into communication strategies, communicators need to focus on continuous learning and maintaining human oversight to ensure that AI serves to enhance, rather than replace, authentic communication. My team subscribes to daily feeds on AI that keep us in tune with trends and solutions. Ultimately, the future of employee communications will depend on the balance between leveraging AI for productivity and maintaining the human touch in communication. By developing AI competencies and embracing ethical principles, communicators can harness AI's potential to create more effective and engaging employee communication strategies. My Parting Advice Three pieces of advice I'd offer to ride this wave: First, stay engaged with time-saving, productivity apps that give you time to invest in more strategic uses like predictive analytics; keep exploring and testing. Second, make new friends with machine learning engineers and computer scientists who can advise and educate you on how to use AI more strategically to solve business issues. And third, lead AI assessment, policy, selection and application through partnership in governance with key functional leaders, and the budgets to which they have access. Forbes Communications Council is an invitation-only community for executives in successful public relations, media strategy, creative and advertising agencies. Do I qualify?
Yahoo
02-07-2025
- Science
- Yahoo
AI might now be as good as humans at detecting emotion, political leaning and sarcasm in online conversations
When we write something to another person, over email or perhaps on social media, we may not state things directly, but our words may instead convey a latent meaning – an underlying subtext. We also often hope that this meaning will come through to the reader. But what happens if an artificial intelligence (AI) system is at the other end, rather than a person? Can AI, especially conversational AI, understand the latent meaning in our text? And if so, what does this mean for us? Latent content analysis is an area of study concerned with uncovering the deeper meanings, sentiments and subtleties embedded in text. For example, this type of analysis can help us grasp political leanings present in communications that are perhaps not obvious to everyone. Understanding how intense someone's emotions are or whether they're being sarcastic can be crucial in supporting a person's mental health, improving customer service, and even keeping people safe at a national level. Get your news from actual experts, straight to your inbox. Sign up to our daily newsletter to receive all The Conversation UK's latest coverage of news and research, from politics and business to the arts and sciences. These are only some examples. We can imagine benefits in other areas of life, like social science research, policy-making and business. Given how important these tasks are – and how quickly conversational AI is improving – it's essential to explore what these technologies can (and can't) do in this regard. Work on this issue is only just starting. Current work shows that ChatGPT has had limited success in detecting political leanings on news websites. Another study that focused on differences in sarcasm detection between different large language models – the technology behind AI chatbots such as ChatGPT – showed that some are better than others. Finally, a study showed that LLMs can guess the emotional 'valence' of words – the inherent positive or negative 'feeling' associated with them. Our new study published in Scientific Reports tested whether conversational AI, inclusive of GPT-4 – a relatively recent version of ChatGPT – can read between the lines of human-written texts. The goal was to find out how well LLMs simulate understanding of sentiment, political leaning, emotional intensity and sarcasm – thus encompassing multiple latent meanings in one study. This study evaluated the reliability, consistency and quality of seven LLMs, including GPT-4, Gemini, Llama-3.1-70B and Mixtral 8 × 7B. We found that these LLMs are about as good as humans at analysing sentiment, political leaning, emotional intensity and sarcasm detection. The study involved 33 human subjects and assessed 100 curated items of text. For spotting political leanings, GPT-4 was more consistent than humans. That matters in fields like journalism, political science, or public health, where inconsistent judgement can skew findings or miss patterns. GPT-4 also proved capable of picking up on emotional intensity and especially valence. Whether a tweet was composed by someone who was mildly annoyed or deeply outraged, the AI could tell – although, someone still had to confirm if the AI was correct in its assessment. This was because AI tends to downplay emotions. Sarcasm remained a stumbling block both for humans and machines. The study found no clear winner there – hence, using human raters doesn't help much with sarcasm detection. Why does this matter? For one, AI like GPT-4 could dramatically cut the time and cost of analysing large volumes of online content. Social scientists often spend months analysing user-generated text to detect trends. GPT-4, on the other hand, opens the door to faster, more responsive research – especially important during crises, elections or public health emergencies. Journalists and fact-checkers might also benefit. Tools powered by GPT-4 could help flag emotionally charged or politically slanted posts in real time, giving newsrooms a head start. There are still concerns. Transparency, fairness and political leanings in AI remain issues. However, studies like this one suggest that when it comes to understanding language, machines are catching up to us fast – and may soon be valuable teammates rather than mere tools. Although this work doesn't claim conversational AI can replace human raters completely, it does challenge the idea that machines are hopeless at detecting nuance. Our study's findings do raise follow-up questions. If a user asks the same question of AI in multiple ways – perhaps by subtly rewording prompts, changing the order of information, or tweaking the amount of context provided – will the model's underlying judgements and ratings remain consistent? Further research should include a systematic and rigorous analysis of how stable the models' outputs are. Ultimately, understanding and improving consistency is essential for deploying LLMs at scale, especially in high-stakes settings. This article is republished from The Conversation under a Creative Commons license. Read the original article. This collaboration emerged through the COST OPINION network. We extend special thanks to network members for helping out with work on this article: Ljubiša Bojić, Anela Mulahmetović Ibrišimović, and Selma Veseljević Jerković.
