Research into Latent Semantic Analytics

Barabasi-Albert model

Over the last year the internet has evolved, a transition which we now all abide by although may not have acknowledged. Content is no longer king, context is.

The sheer volume of data being created each minute is staggering (check out this infographic) and techniques are constantly being developed in order to search and organise this data. In the PR industry it is critical to keep an eye on all data relating to clients, surrounding topics and key influencers. The vast amount of content avaliable makes this task easy but only if easy search solutions exist.

For my dissertation I researched a very new area of online analytics called Latent Semantic Analytics. The process has existed for decades but only a handful of organisations have managed to use the mathmatical technique for business means. Within my dissertation I explore the benefits of Latent Semantic Analytics by how the process can create relationships between words depending upon their frequency and contexts.

I managed to gain a First for this piece of research and I am pleased to be able to share it with you all online today. Not only do I hope you find the content of my dissertation interesting but current PR students may find it useful to read in terms of the structure I used.

Feel free to share this post with anybody you think would be relevant and if you have any questions I will try my best to answer them!

Michael is a Consultant for Keene Communications where he devises and manages digital public relations campaigns. Keene Communications has been providing public affairs, public relations and representation services for over 25 years. Michael is a certified member (MCIPR) of the Chartered Institution of Public Relations (CIPR).