|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/sentiment-analysis-deep-learning-keras-python/
课程评论：没有评论
课程名称：通过Keras与Python进行情感分析 课程概述：您是否想学习情感分析？如果您在任何商业领域工作，答案几乎总是“是”。每家公司都希望了解客户对其产品和服务的感受，而情感分析是找到答案最简单和最准确的方法。通过学习情感分析，您将为任何公司变得不可或缺，特别是那些关注产品质量保障及商业智能的公司。 在本课程中，我们使情感分析变得简单易行。在第一段视频中，我们介绍了一个少于60行的情感分析引擎，它可以执行行业标准的情感分析。课程的其余部分将详细解释这60行代码，以便您彻底理解代码的工作原理。完成课程后，您将能够将此系统快速集成到现有流程中，分析您所提供的任何文本。 该课程重点强调使用Python进行情感分析的优势。与R语言相比，使用Python编写情感分析引擎可以更轻松地将代码整合到最终的业务产品中。此外，我们还会使用深度学习模型来进行情感分析，您只需付出很少的努力，就能获得行业标准的情感分析，并且可以随着更好的模型的出现，方便地改进您的引擎。 我们将专注于以下内容： - 轻松编写行业级情感分析引擎 - 最基础的机器学习知识，涉及最少的数学 - 理论与实际应用的结合——如何在现实世界中使用情感分析 - 避免新手常犯错误的建议，以及最佳实践 讲师简介：该课程的讲师是一名教师和研究者，拥有安全领域的博士学位，并在德国马克斯·普朗克软件系统研究所获得博士后。具有17年以上计算机工作经验和15年以上教学经验，专注于深度学习领域5年以上，曾使用几乎所有现代工具，并在Udemy上拥有畅销课程。 目标受众：任何想在现实世界中进行情感分析的人，想了解深度学习如何帮助情感分析的人，以及希望看清自己产品在客户中的表现的公司员工。 学习要求：课程将涵盖Python基础知识（安装、条件语句、循环、列表），不需要具备机器学习背景（但理论内容保持在最低限度）。
Do you want to learn to do sentiment analysis? The answer should almost always be yes if you are working in any business domain. Every company on the face of the earth wants to know what its customers feel about its products and services - and sentiment analysis is the easiest way and most accurate way of finding out the answer to this question.By learning to do sentiment analysis, you would be making yourself invaluable to any company, especially those which are interested in quality assurance of their products and those working with business intelligence (which is almost all sensible companies, large and small, nowadays).And in this course, we make doing sentiment analysis really easy. In the very first video, we introduce a less than 60 line sentiment analysis engine that can perform industry grade sentiment analysis. We then spend the rest of the course explaining these very powerful 60 lines so that you have a thorough understanding of the code. After you are done with this course, you would immediately be able to plug this system into your existing pipelines to do sentiment analysis of any text you can throw at it.That is one of the reasons you should be doing sentiment analysis using Python and not some other "data science language" such as R. If you work with R and do sentiment analysis, you would still have to put in a lot of effort to take this skill to the market. If you write your sentiment analysis engine in Python, incorporating your code into your final business product is dead easy.The second important tip for sentiment analysis is the latest success stories do not try to do it by hand. Instead, you train a machine to do it for you. That is why we use deep sentiment analysis in this course: you will train a deep learning model to do sentiment analysis for you. That way, you put in very little effort and get industry standard sentiment analysis - and you can improve your engine later on by simply utilizing a better model as soon as it becomes available with little effort.We will focus on the following:Understanding how to write industry grade sentiment analysis engines with very little effortBasics of machine learning with minimal mathUnderstand not only the theoretical and academic aspects of sentiment analysis but also how to use it in your own field - real world sentiment analysisTips on avoiding mistakes made by new-comers to the field and the best practices to get you to your goal with minimal effortAbout the instructor:Teacher and researcher by professionPhD in Security and a PostDoc from Max Planck Institute for Software Systems, Germany17+ years of working with computers and 15+ years of teaching experience5+ years of working extensively with deep learning. I worked with almost all the modern tools as soon as they were releasedBest seller instructor on Udemy with many highly rated courses! Target Audience:Anyone who:wants to do sentiment analysis in the real worldwants to understand how deep learning can help with sentiment analysisis working for a company that wants to see how its products are doing with their customersWhat you need to know:Python basics (installation, if, loops, lists) - Everything else will be covered in the courseNo machine learning background is assumed (but we keep the theory to a minimum)
