Blog post 1: What is social media analytics?

With the rapid development of Internet and other advanced information technology, the form of media has been changed. Twitter, amazon online shopping, and even wikipedia have gradually taken the most place of tradition media in people’s daily life. On account of prosperous growth of social media, more and more scientists and engineers choose focus on this field, which, on the other hand, leads to social media analytics.

According to IEEE’s relevant definition, social media analytics is about making and assessing information framework or tool to extract hidden key information from a large amount of semi-structured and unstructured data collected in social media services in order to develop meaningful and significant decision making (IEEE Intelligent Systems,2010). Apart from that, this process is normally driven by the exact targets and requirements from desired practice. One feature that resembles social media is that they both involve humanities and technologies. However, the other that doesn’t is that social media analytics focuses more on “analysis” component such as natural language processing, sentiment analysis & opinion mining algorithms, social network analysis and recommendation and ranking.

Generally speaking, the social media analytics process (Alice, 2016) contains (1). listen with a purpose. Before starting this procedure, it is significant to assume that the aim within receiving from social media.(2) gathering data. gathering data is a hard experience which often consumes lots of time and is easily influenced by human error. Using software may be a good way out. (3) organizing data. The following procedure is to organize the data into relevant categories. (4). interpreting data. Many interactions could not be kept out for interpretation as it is often from a larger data trail or conversation in which the wider context needs to be understood. (5) action the data. Now that the data has been gathered and interpreted, it will be measured against the original corporation aims, with considering to be paid to how consequences connect to other departments within the business.

And the techniques of it are (1) Computational science techniques. Automated sentiment analysis of digital texts uses elements from machine learning (Turney 2002).

(2) Sentiment analysis. Sentiment is about mining attitudes, emotions, feelings—it is subjective impressions rather than facts. Generally speaking, sentiment analysis aims to determine the attitude expressed by the text writer or speaker with respect to the topic or the overall contextual polarity of a document (Mejova 2009).

References

1.D. Zeng, H. Chen, R. Lusch, and S.-H. Li. “Social Media Analytics and Intelligence”, IEEE Intelligent Systems, vol. 25, no. 6, 13-16, 2010.

2.Alice (2016) how to perform a social media analysis – in 5 steps.

3.Turney PD (2002) Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics pp. 417–424.

4.Mejova Y (2009) Sentiment analysis: an overview, pp 1-34. Accessed 4 Nov 2013.