In a week I will be attending the 1st International CIKM Workshop on Topic-Sentiment Analysis for Mass Opinion Measurement ... or TSA for short. It's been put together by some top names in the area, and there are some very interesting looking papers on the program ... not least of which is my paper of course: Scary Films Good, Scary Flights Bad: Topic driven feature selection for classification of sentiment.

I shall endeavour to write up anything interesting that I see/hear/learn/discuss once we get back (and we shall be reporting on the travel/culinary side over at Exit Music). It's getting quite late to register, so if this is the first you've heard of TSA then I apologise for not mentioning it sooner. If you'll be going, however, then I'll see you there!

Did I mention that the paper Alastair, Jon and I recently wrote was accepted for this years ICWSM conference? No? Well it was. I'm hoping to make it over but there are a few things to work out here first. Either way the esteemed Dr Gill will be presenting on our behalf. It's looking like a pretty interesting conference, and the reviewers certainly showed great interest in our work.

Ok, so I maybe didn't mention that, but surely I told you about the other work that is happening around the world with my fellow blogademics? Did I not? I could have sworn that I told you about the work up in Calgary looking at non-literal language (for example sarcasm and hyperbole) in blogs; and the studies being conducted in personality classification in Chicago following the work on our 2007 paper with our large dataset. There are a few posters and papers in the offing and I'll definitely tell you more as things develop.

I certainly know I haven't told you anything about what I've been doing recently at work. I too am following up all my previous work on socio-biographic classification of text. We've been undergoing a program of redevelopment on some of our language processing software, and I'm very much enjoying being at the heart of it. Things are shaping up nicely.

I am fully aware that posting has been thin on the ground in recent (and not so recent) times. Well I'm here to bring you the first in a series of posts to discuss the latest developments.

That's right, there are actual developments.

Increasingly I have come to realise that I possess some pretty unique data, and if I'm not working on it then it's a shame to let it go to waste. My first venture into new collaborative thinking came about when Alastair (Dr Gill to you) provided me with a data sharing opportunity.

And so it comes to be that my corpus is currently with some friendly researchers at the University of Calgary. Juanita Whalen, having recently looked into email with Alastair, is currently exploring the use of non-literal language in personal blogs. I've only seen some cursory findings but they are very interesting and seem to correspond with a few things I've previously found in the same data.

Watch this space for more details ... I promise there will be more details.

Moving from academia to industry has meant a number of changes, not least of which is that there are fewer opportunities to publish research. (Did you think I was going to say something about my lack of blogging here on Blogademia? Well, I will admit that this did cross my mind, but this is a kind of publishing so I felt it was adequately covered.)

I always meant to carry on with my blog studies, because I'm still very interested in the area, but the most I've been able to do recently is review for various conferences (I hope some of you made it to ICWSM this year) and journals. However, by the power of "it's not what you know but who knows about what you know" this activity brought me an offer I found hard to resist.

One of the editors that I've reviewed for is putting together a collection of new works to publish as a book. Since it's in the area of pragmatics and computer-mediated communication, and they know this is exactly what I do, I was asked to consider putting in a proposal for a chapter. It's one thing to find an opportunity like this, but it's quite another be directly invited. Both honoured and excited at the possibility, I accepted. Writing a chapter about the language of weblogs (now that sounds good ... I might have a title there :) ) should be right up my street, and would be a great way to immerse myself back in my role as a blogademic.

This was a little while ago, but I just got the decision email the other day. Now it's not the case that I wouldn't be blogging this if the answer had been "thanks but no thanks", but I think you can probably guess what that decision was. And so you find yourselves with the very exciting possibility that you will be able to go to a book store and actually buy a little piece of my wisdom. I'm so excited for you :)

Blogademia ... now that's a name I've not heard in a long, long time. I'm always torn between posting something here to keep it going, and wanting only to post stuff worthy of posting. With the change of jobs, I've been kept nicely busy in recent times, and so my blog work has fallen by the wayside. Not my interest ... oh no ... I'm still really into social media, I'm still a sociolinguist, and I will get to pursue sentiment analysis in time. I'm just not sure when I'll get to write again. I've a few opportunities coming up - my grip on my data finally loosening - as both Jon and Alastair are beginning to work with people interested in continuing our group's interest in the area.

For my own part, I've mostly been playing the part of reviewer in recent times. It's quite an honour to be asked to review on the topics and for the specific publications I've been asked to do. I do have a very niche area of expertise, which I guess makes me a go to guy for such things. Along with all the individual papers though, I'm also on the committee for the international conference on weblogs and social media to be held in Seattle next year. Keen blogademics will know that I attended last year along with Sam Gosling. It seems our work of a more psychological bent has helped shape the direction of this years conference, and there has been a significant increase in submissions in this area.

This is two edged blade of course. It is great to see more people doing work in this area, slowly building the profile of psycho/sociological work in online environments. It will be fascinating to read these papers to see what new directions people are moving in. However, the big disappointment is that I probably won't be going this year. I know, I know, this is saddening news but just because there will be no Nowson does not mean the rest of you shouldn't go - trust me when I say this one is going to be good!!

I though it was high time I shared my news with you, and you might want to sit down for this. Are you ready? I'm leaving academia.

What do you mean you weren't ready? I gave you ample bracing time.

Anyway, it's not as bad as it sounds. Basically my life at Macquarie has run its course, and it was obvious a while back that it was time to move. And move I am. And while I am going to be leaving academia my recent work has not been concerned with blogs or personality anyway. And as you can tell from the updatedness of this blog in recent times, it's not like there's been a great deal to report. With the work I've been doing, there's just been no time. It's something that if you don't experience as a post-doc, you're very lucky.

But all that will change I promise. While I can't say exactly what I'm actually going to be doing in my new role (anyone that's worked in/with industry will be familiar with the restrictions of an NDA) I can tell you that it is much - MUCH - closer to my own research interests. It should also give me more of an opportunity to get back in the game by pursuing some of my own work. And I'm still enjoying (and available for) reviewing, so have plenty of motivation for keeping the Nowson Blogademia names out there. In fact, I have a number of ideas for collaboration that I might now get a chance to pursue ...

MySpace removes 29,000 accounts of sex offenders. Rearrange those words in countless ways and you have the myriad headlines that surfaced across the internet last week. I don't pretend to know all the details, and I'm certainly not going to get into any discussions of 2nd chances or something like that. No, I come at this story from purely objective academic interest.

There is increasing interest in detecting undesirables on the internet. I've seen adverts here, in the UK and the US which are essentially making it clear that internet chat rooms, for example, are monitored. You've all seen the adverts, with adults speaking with a kids voice. It IS a dangerous world out there, and people do need to be careful online.

It seems that to take a stand and be seen to be doing something, MySpace deleted profiles of known sex offenders. Whether or not they knew about these because people used their real names, had suspicious interests or some other cunning plan, is not clear. What they have done by doing this, however, is create a ready made corpus of profiles of undesirables. This is exactly the kind of data that academics would love to get their hands on. If you want to be able to detect something, you need to have concrete examples of it. But it is hard to go out yourself and find such data. I doubt that this "corpus" will ever become publicly available but they have it there, ready to go. Imagine what you could do with this.

And imagine you will have to, because I'm not giving you any of my ideas.