Archive for the ‘social’ Category

3 things I remember from ICWSM (4th-7th June)

Wednesday, June 27th, 2012

Three weeks after the conference, here is what is still clear in my mind and left from my notes. These are my three big take-aways:

1.     Robin Dunbar’s Invited Talk

A much anticipated talk by Dunbar (the Dunbar number http://en.wikipedia.org/wiki/Dunbar%27s_number), full of fun yet important research. I am not sure how much of it was done by Dunbar himself but this is more or less what the talk was about:
Social grooming online (interesting analogy with ape grooming behaviour here); As little as “liking” someone’s photo online can help sustain a relationship over distance. This online “grooming” can also increase social capital. This is more easily done by women, who can sustain a friendship with another female entirely based on distance communication e.g. phone conversations (thus the higher social media usage for females too), on the other hand male friends need to engage in activities with one another to sustain the relationship e.g., go to the pub and watch a game.  As male and female call times and patterns were compared, there was laughter in the audience due to the sharp contrast (you can imagine which was higher). This has obvious implications for how male and female social networks change over distance.

Robin Dunbar Presentation

Robin Dunbar taking questions from the audience

Social investment in romantic relationships is higher from women at the beginning and shifts later in the relationship (possibly after childbirth). Evidence shows that males are much more passive when it comes to choosing a mate, whereas females do most of the work associated with finding and keeping a partner. Entering in a romantic relationship also costs you two friends. Human capacity for giving attention in sustaining relationships is limited and a lot of investment is required for “securing a mate”, at an

estimated cost of two friends (one friend and one family member usually). This is also where the Dunbar number comes in. It was pointed out that you can’t tattoo more than 150 Facebook profile pictures on a standard arm, another validation of the number (see http://abcnews.go.com/Technology/facebook-tattoo-hoax-video-woman-friends-pictures-tattooed/story?id=13795834 to get this).

Extra Dunbar wisdom: 1) If you want to be the next Nobel prize winner, invent “the virtual touch” 2) Change academic fields every seven years 3) Laughter turns strangers into friends, sense of humour is the strongest homophilic bond

2.     Igor Perisic (LinkedIn), keynote talk

Despite being the only person in the audience not familiar with LinkedIn, I really enjoyed this talk because LinkedIn seems to be a transparent and data-rich platform.

It was pointed out that recommender sites (e.g. dating sites) give you 2nd or 3rd best match to keep you happy yet coming back for more (not sure if LinkedIn does this with jobs?);
If one of your colleagues leaves, you are at high risk of leaving in the next six months;
A gravity model was presented – where you are likely to go/stay for work using LinkedIn recommendations;
The length of your name/your name could determine how successful you are/what business you might go in (to consider when picking baby names)

3.   The state we’re in.

I haven’t been long in this trade but

some things that stood out to me as “novel” were:

1) The idea of “social web” promoted by Google (or Google’s Andrew Tomkins to be politically correct). This means that everything from banking to retail will be embedded in a social network that is task-oriented, so all those hours spent on social media will be more productive (It wasn’t stated specifically how). Question-asking online and bringing bots into social media was  also demonstrated in SearchBuddies: Bringing Search Engines into the Conversation, and the effects of this method were evaluated. The whole concept of “social web” emerged as the future of social media during the conference.
2) We often look at one platform and reach global conclusions, in Crossing Media Streams with Sentiment an important reminder of cross-platform analysis was given. Twitter, Blogs and Reviews were explored to demonstrate these differences. Attention needs to be given when giving titles to papers, not to overstate the impact of findings e.g. “Social Media Sentiments”, when only Twitter is analysed in the work.
3) Is privacy virtually dead? If even our privacy settings can reveal who we are, is there any way to remain private online? This is something that came to mind during Daniele’s talk and later in discussion of the digital divide and browsing behaviour in Who Does What on the Web. Not only gender but also ethnicity, education (and much more) can be derived from browsing behaviour.  In Grief Stricken in a Crowd, the grieving process goes online and language can be analysed to detect those in need of counselling or help. I suppose social media analysis will soon be able to tell us more about ourselves than we know.
And the rest was as ordered…

Bar view at the top of the Guinness Storehouse

Deconstructing “the Twitter revolution”

Tuesday, July 7th, 2009

Hamid Tehrani of Global Voices gives a sober assessment of the role of Twitter in the Iranian election protests. One of the issues he raises is the temptation to relay breaking news without verifying it. The open source Ushahidi project, which was initially developed to aggregate and map reports of violence following the Kenyan elections in 2007/8, has proposed crowdsourced filtering to deal with this problem. However, the question remains, how can the people aggregating and filtering first-hand reports determine what’s true? Does citizen journalism still require a layer of professional editors, experts and fact-checkers, or can all these functions be shared among the crowd?

socialcom09

Monday, June 29th, 2009

The program of SocialCom is out. My picks:

  • Deriving Expertise Profiles From Tags (adriana.budura@epfl.ch)
  • Ranking Comments on the Social Web (khabiri@cse.tamu.edu)
  • Structure of Heterogeneous Networks (lerman@isi.edu)
  • Online User Activities Discovery based on Time Dependent Data (csdhong@cse.ust.hk)
  • Evaluating the Impact of Attacks In Collaborative Tagging Environments (mramezani@cdm.depaul.edu)
  • Community Computing: Comparisons between Rural and Urban Societies using Mobile Phone Data (nathan@mit.edu)

Wireless music-sharing

Monday, May 11th, 2009

Instead of sharing music in front of a computer, what if you could simply share songs, directly from your MP3 player, with friends and other people you encounter in your everyday life? Maria’s research answers this question:  mainstream article & research pdf

Dataset and R code for our paper on genres/artists affinity

Tuesday, August 19th, 2008

Justin Donaldson and I have a paper at ISMIR entitled “Uncovering affinity of artists to multiple genres from social behaviour data”. The paper details a project we worked on for the past year or so involving popular music listening activity from a pool of MusicStrands users.

We provide not only the paper, but also the dataset and the code used in our analysis. All of this is available at the website we have set up for the project: http://labs.strands.com/music/affinity/

The main contribution of the project is an analysis and illustration of genres as “fuzzy sets” rather than boolean labels. Through a co-occurence analysis of hundreds of thousands of user playlists, a frequency based “affinity” metric is formed between artists and genres. This affinity metric is a more detailed expression of the style of a given artist’s music. The idea and awareness of predominant genres are a trivial part of any person’s understanding of the vast corpus of popular music. However, genres typically are used as Boolean categorical labels. I.e. an artist is understood to be associated with only one given genre.

By expressing a connection to multiple genres through our affinity metric, a more detailed picture of the artist emerges. We give a lot more examples in the website, so be sure to check it out. - http://labs.strands.com/music/affinity/

 

Claudio Baccigalupo

Seminar: Social Urban Computing

Friday, May 23rd, 2008

Please join us for a seminar on the 27th of May (Tuesday) at 2pm in Room
6.12 (UCL Dept of Computer Science) .

Abstract
Arianna Bassoli
Information Systems and Innovation Group
The London School of Economics and Political Science

In this lecture I will present my work in the area of ubiquitous and urban computing design. Starting from the approach used – social computing – which values the adoption of social science methods for informing design, I will move on to describe some of the mobile peer-to-peer applications I created: including an application allowing users to tune in to the music that other people around them are listening to, and a much larger scale system for sharing music on, in, and through the London Underground.

(paper in pdf)

Information Overload

Tuesday, February 26th, 2008

Many of us are researching ways of reducing information overload. The next The Economist Oxford-style debate revolves around information overload. The proposition: “This house believes that if the promise of technology is to simplify our lives, it is failing.” The pro speaker: Richard Szafranski (Toffler Associates). The con: John Maeda (MIT). (more…)