实例探究 > Appenza Studio & Ministry of Education, Egypt: Semantic Video Content Search & Sentiment Analysis Solution

Appenza Studio & Ministry of Education, Egypt: Semantic Video Content Search & Sentiment Analysis Solution

公司规模
11-200
地区
  • Africa
  • Middle East
国家
  • Egypt
产品
  • Semantic Video and Content Search (SVACS) Solution
  • Arabic Sentiment Analysis Model
  • OCR Model
技术栈
  • Machine Learning
  • Natural Language Processing (NLP)
  • Speech-to-Text
  • Optical Character Recognition (OCR)
实施规模
  • Enterprise-wide Deployment
影响指标
  • Customer Satisfaction
  • Digital Expertise
  • Productivity Improvements
技术
  • 分析与建模 - 机器学习
  • 分析与建模 - 自然语言处理 (NLP)
  • 应用基础设施与中间件 - 数据交换与集成
适用行业
  • 教育
适用功能
  • 产品研发
  • 质量保证
服务
  • 数据科学服务
  • 软件设计与工程服务
  • 系统集成
关于客户
The client is a specialized mobile app and web development company, Appenza Studio, headquartered in Cairo, Egypt. They have a strategic presence in the UK, US, Europe, and MENA (Middle East and North Africa), and partner with both private & public organizations. Appenza is a partner to the Egyptian Ministry of Education in developing mobile learning apps that can be used by students and their wards to access the Ministry’s repository of academic material. The Ministry invests heavily in e-learning with interactive programs, virtual lessons, and electronic books. They consider education crucial to the nurturing of the future generation of Egyptians and have a rich database of academic resources.
挑战
Being in the business of educational technology catered to the end-user, it was essential for Appenza to listen to the voice of the customer to create an engaging and efficient learning app. However, for the development of the app itself, the large reservoir of the Ministry’s academic content needed to be accessible to users. The challenge could be categorized in two ways: Search & Discovery of Content: The Ministry of Education has an immense source of education material across a wide variety of subjects ranging from Literature to Maths. All of this data is maintained in a knowledge bank (KB) for students from Kindergarten to Higher Secondary (Grade 12) in PDFs and videos. While the content was quite rich and informative, it was nearly impossible to discover since none of it was structured by any theme or logic. There was no search facility to dive into the individual content as well. Added to this, the content was a mix of Arabic and English, which made organizing the content more difficult. Understanding User Feedback: It was imperative that Appenza understood the feedback from students and parents for the new and improved mobile app being created for the Ministry of Education, and to measure its performance on an ongoing basis. They, however, did not have the technical know-how to measure public sentiment across the country expressed in thousands of comments on different social media platforms and review websites. They needed an accurate and automated sentiment analysis especially made for Egyptian Arabic, along with an English model for gathering insights from the mined social media data.
解决方案
Upon analyzing the situation, Repustate came up with a two-step strategy: Create a semantic search solution that could analyze both Arabic and English text. Custom-build an Arabic sentiment analysis solution to capture the public sentiment around the learning app developed for the Ministry. Phase 1: Repustate realized that the fundamental problem of the Ministry of Education was having no search facility to dive into the individual PDFs and videos in the massive Knowledge Bank, in neither Arabic nor English. Repustate planned and developed a semantic search solution that allowed parents and students to access the entire KB and search for content in both languages. The Semantic Video and Content Search (SVACS) Solution captured and organized all the content, regardless of its format. In doing so, the entire collection of resources was available to the users for search and retrieval clearly identified by themes, topics, and language. Phase 2: Repustate developed a customized Arabic sentiment analysis model for Appenza. It allowed them to measure the number of social media mentions for each of the topics they wanted to analyze, as well as the public sentiment around it. This was one of the most important features of the overall solution that Repustate provided. The insights gathered from the model are what Appenza used as guidelines for improving and enhancing the features and user experience of the learning app.
运营影响
  • The entire repository of the Egyptian Ministry of Education is available for search and retrieval in both Arabic and English.
  • The solution turns large video archives into new content by semantically classifying and organizing the video content. Thus enabling the Ministry to leverage existing archived videos and remodel them for current use.
  • Appenza can measure the performance of the mobile app and drive continuous improvement in the user experience and design.
  • Based on aspect-themed sentiment scoring, both the Ministry and Appenza can prioritize targeted strategic future improvement in quality for parents and students.
  • Repustate’s solution has helped bridge the gap between the Ministry and the Egyptian population in the efficacy of education outreach. Through Repustate’s Arabic natural language processing model for semantic search and sentiment analysis, the Ministry caters to both its Arabic and English speaking population in a more holistic way. They are also able to nurture connections between academic institutions by giving them equal attention and levels of engagement.
数量效益
  • The entire repository of the Egyptian Ministry of Education is now searchable in both Arabic and English.
  • The solution enables the Ministry to leverage existing archived videos and remodel them for current use.
  • Appenza can measure the performance of the mobile app and drive continuous improvement in the user experience and design.

Case Study missing?

Start adding your own!

Register with your work email and create a new case study profile for your business.

Add New Record

相关案例.

联系我们

欢迎与我们交流!
* Required
* Required
* Required
* Invalid email address
提交此表单,即表示您同意 IoT ONE 可以与您联系并分享洞察和营销信息。
不,谢谢,我不想收到来自 IoT ONE 的任何营销电子邮件。
提交

感谢您的信息!
我们会很快与你取得联系。