Better Education Experience with Digital Environment


For years education in Hong Kong has been stereotyped as feeding method, where teachers prepare educational materials, grade students’ work, and give feedback, and students learn from what they are provided. However, this kind of education is not effective at all. Teaching is restricted to the variation between the levels of students. Students, on the other hand, have been pushed through a “one-size-fits-all” type of learning, not personalised to their abilities and needs.

Application of Machine Learning in Education

The fast growing digital environment can help transform the learning experience of students. In a digitised classroom, teaching can be more personalised and provide far more effective learning. The tools are also affordable and easily accessible.

  1. Mobile learning provides access to learning while on-the-go

    As a new generation learner, I understand that we are always pressed for time, balancing between professional and personal priorities. We prefer learning in our own pace rather than being told what and when to do.
    Therefore, mobile learning is important when it comes to this point. We can learn what we need and what we are interested anytime, anywhere.


  1. Gamification makes the learner a game player, thus making learning fun, rewarding and possibly addictive

    I can never deny that playing is far more attractive than learning in piles of books. However, with more advanced technology, many learning-related games are made to make it more interesting than it should be.

    Game-based learning: ST MathMangahigh

  1. Dynamic scheduling matches students that need help with teachers that have time

    Screen Shot 2017-03-10 at 11.34.36 PM.png

    Instead of sending emails to ask for help from tutors and professors, learners can schedule a meeting time with teachers that are available. This is more convenient compared to the traditional way.

    NewClassrooms uses learning analytics to schedule personalised math learning experiences.



Successful education requires understanding on the needs of the new generation. Digital learning will accelerate the responsiveness of learning and provide a more personalised learning. This acceleration will also encourage learners to be proactive in updating their knowledge and competencies. I believe it is important to discuss the potential of machine learning in different fields so as to bring out its implicit qualities in the future.






The use of Sentiment Analysis in Social Media Analysis



What is Sentiment Analysis?

First, we need to know what sentiment analysis means. According to the Oxford dictionary, sentiment analysis refers to the process of computationally identifying and categorising opinions expressed in a piece of text, especially in order to determine whether the writer’s attitude towards a particular topic, product, etc. is positive, negative, or neutral.

In order words, it is the process we determine the emotional tone behind a series of words and gain an understanding of the writer’s view and attitude behind the limited expression.


The use of Sentiment Analysis

Undoubtedly, sentiment analysis is widely used nowadays. It allows us to gain the opinion of the public over certain topics. We can get the answer very quickly. One of the most common examples is Facebook.1

As shown in the above figure, we can immediately react to the topic and show our feelings.


Is sentiment analysis always reliable?

Human language is complex. Sometimes we humans interpret the wrong meaning in both spoken and written language, teaching a machine to interpret the tone behind words is even more difficult.


“Anyone who says they’re getting better than 70% [sentiment accuracy] is lying, generally speaking” Source:


I guess 50-60% of accuracy won’t be convincing when you are making some important business decisions. The result can be disastrous if we are making decision based on inaccurate sentiment analysis.

So, we should be aware and understand the methods the social media ventor is using. There are many methods and here I would like to discuss two of them.


  1. Keyword Processing

In this method, words are categorized as ‘positive’ or ‘negative’. Then, it determines the overall percentage of positive or negative words in a passage.

This method is fast and cheap to implement. However, it may not be useful when dealing with double positives or doule negatives.


  1. Natural Language Processing (NLP)

NLP is another method that makes the computer understand natural language input and generate natural language output. In order words, computers can get the meaning of human words, as it understands that several words form a phrase, several phrases form a sentence, and sentences express ideas.


Though NLP seems reliable, it still has limitations. For example, it cannot interpret sarcasm and acronyms. Consider the sentence: “He has no enemies, but is intensely disliked by his friends.” We can understand “friends” do not mean a true friend here but the computer will not inerpret the same meaning.




While sentiment analysis becomes more popular nowadays. As an analyst, we should choose a suitable method carefully so that the result can be more comprehensive and reliable. As a user, we should choose a vendor that treats sentiment analysis seriously and is capable to update their technology regularly.

As college students, how can social media benefit our learning?

As a college student, I believe our learning method is much different from that of secondary school, where we are given notes and exercise and being tested. However, in universities, we are often given the syllabus and notes, then we self-learn, ask questions and do the assignments.

In this process, social media really provides much help. As mentioned in lecture, information actions involve one-to-one, one-to-many, many-to-one, or many-to-many human information actors. These are all useful ways of learning.


In traditional way, we can read from a textbook, which is often written by an expert or some scholars.

Nowadays, the most common way is to read the documents online to find a solution or to learn something quick.



There are many forums nowadays where we can discuss our problems online and get feedback. For example, when you have problems with downloading or using software, you can ask this specific question online and wait for a response. This is a fast learning process. However, there is a potential risk that the answer or suggestion provided is not perfectly correct.



If you want a correct answer, you better send email to your professor directly. This would be a one-to-one communication where you would expect a response or at least acknowledgement of understanding.


“What is Human Information Interaction and why is it important to me?”

Human information interaction (HII) is a study that focuses on people’s relationship with information, rather than with technology (as in human-machine interaction). HII is inherently a multidisciplinary field, encompassing areas such as human-computer interaction (HCI) and computer-supported cooperative work (CSCW).

During the lectures, I have learned more about HII and the elements in it. The first thing I aware is that without HII, people can easily get confused if the information has get to the destination or not. HII can help us develop a better system and alleviate the three interrelated levels of communication problems (the technical, semantic and effectiveness problems). These studies can allow us to learn more about communication, so that we can help fix or even develop a better system in the future.

Besides, I am quite impressed by Shannon’s Information Theory where information is defined by a reduction in uncertainty and the change brought by informational energy is reduction in uncertainty. To me, information is an abstract term that does not have an actual meaning. However, the calculations of probability has quantified ‘information’. The concept of Entropy and information content made the calculations even more precise. Overall, it can allow us to understand and compare information in different cases more easily.

Lastly, in general, HII has brought benefits to build better communication systems. It can surely enhance our quality of life in many ways. For example, as a student, I can easily obtain knowledge through other people’s webpage and forums. As general citizen, I access different information from website and gain knowledge from all over the world. HII can improve social media and therefore is important to our daily lives.