Social Network Anylysis With Mathematics

It seems that social network has no difference with other web sites. However, we can study the deep mathematical principle in it, which will make a great contribution to the promotion of marketing.

We regard network just as a graph. There are nodes, which are connected to form edges. In a social network, each individual is a node, people are connected to each other in accordance with friend relationship. 

Each node has ? edges. The more edges, the greater connectivity. Just like the more friends you have, the greater influence you have. For example, we issued a free trial sample to consumer. If the consumer feels satisfied, he will buy it, and recommend to his friends. As the manufacturer, we certainly hope that the samples are distributed to more influential people, because they will be passed on to more nodes, which will bring more potential customers. We know that graph includes directed graph and undirected graph. The difference between them is whether the links between nodes are bidirectional. Facebook and Renren are undirected graphs: If you are my friend, I am your friend. However, Twitter and Sina Weibo are directed graphs: I follow some people, and there are also people follow me. This is a relationship from one node to another node, not reversible.

For example, Zhao Te is followed by many people on blog, then there are many nodes pointing to him, who is on a high in-degree centrality. However, in-degree high node is not always the most valuable. Another example, an article has a high in-degree. A lot of people have quoted this paper.This article may cover a valuable question to research, but it may make ​​obvious mistakes so that everyone having read the research paper will say: "Go for a look of this article, the author is so funny!"

Taobao & Aliwangwang

Perhaps people do not know Alibaba very well, but nearly each Chinese netizen is familiar with Taobao.It has become the largest online retail shopping district in Asia. Taobao's original intention was for the large number of ordinary users and companies, everyone can use this populist platform. Since the state stepped up efforts to regulate SMS, making a large number of small and medium sized websites and personal websites lost their source of profit and unsustainable. Taobao gave small advertisement to the site above. Through advertisement, consumers learnt such an e-commerce site.

Due to the network effect, Taobao continues to become stronger and stronger since the amount of network users is growing larger and larger. While users are increasing, resources in this market will be more abundant, the market mechanism will satisfy consumers more, and the entire transaction will be more and more famous.

Aliwangwang is one of the greatest success of Taobao. It is a space for multiplayer to exchange their ideas. Individuals have the same fun, make friends and chat about sale. Users can not only expand friend circles, but also create own store base, timely promoting the latest baby announcement by the group. When joining the group, people can get new information quickly from other friends. Either buyer or seller can exchange life and working experience.

Difficulty In Sentiment Analysis & Opinion Mining

When I want to pick a film, I always go to DOUBAN for reference. Firstly, I will focus on which style of film would attract me better through finding the key words. Then I will compare the scores of films. Finally I will read some comments of films having a high score.

Recently more and more individuals prefer shopping online. I think many people also visit similar platform to gain some information before making their choice, just like my picking films. Our opinions and behaviors are influenced by others'. Therefore, sentiment analysis is increasingly valuable to study.

Through the fourth course, we have learnt relative knowledge in the field of mining opinion. I want to take DOUBAN mentioned above as a example. How to deal with the enormous comments? In an intuitive sense, adjectives represent the sentiment. In addition, we regard unigrams as the feathers, because they are more simple and give satisfactory results. And we have to dispose the negative sentences. We add NOT_ to every word between negation and following punctuation. "don't like this movie" is changed to "don't NOT_like NOT_this NOT_movie". Then we can use an appropriate classifier to finish the classification：

However, sentiment analysis is not that easy. When browsing the web pages, I found so many euphemism or sarcastic comment. "If you are reading this because it is your darling fragrance, please wear it at home exclusively, and tape the windows shut." The writer runs the gamut of emotion from A to B. "This film should be brilliant.  It sounds like a great plot, the actors are first grade, and the supporting cast is good as well, and Stallone is attempting to deliver a good performance. However, it can’t hold up." I expecte a communication with classmates, who have some ideas of solving this problem.

My Thoughts on Social Media Analytics

After three courses taken, I have learnt a lot about social media analytics. It is my pleasure to share my opinions with you.

Along with the advance of the society, we are now living in a world of numerous messages. Everybody uses social platform to get and share informations related with him. More and more netizens have been used to social software, such as Facebook, Google+, Wechat and Qzone. We can acquire great data from these social circles, which will make a amazing contribution to learning more about users' thoughts and improving our service.

However，how to deal with such an enormous data resource? As we know, text content is easier to analyse. Here natural language processing is required. It is a field that involves computer science, artificial intelligence, linguistics, human-computer interface and so on. Through taking NLP, we can learn customs' ideas, sentiment and behavior. To complete what mentioned above, we also have to dispose the useless words and punctuation.


In order to compare the documents, we are to classify the text, using vector to estimate terms and method of probability and mathematical statistics. In addition, clustering can finish it without labelled data. During learning K-Means clustering algorithm, I thought of the knowledge of pattern recognition. They apply the similar method to divide the items into any clusters. And they are both unsupervised, in relation to artificial intelligence. The second figure shows us how the pattern recognition works. Though the objects they dispose are different，they both reflect the application of function and the beauty of mathematics.

Social Media Analytics is a advanced and practical course. I do believe I will enjoy the course and reap no little benefit.