Methodology: Draft/Free writing (part 1)

This entry was posted by Laura on Tuesday, 13 July, 2010 at

One of the ways I learn best is by talking through a problem.  I compare and contrast things.  I ask people their opinions.  I read things to people.  I get into in depth conversations about practices.  I ask questions.   Write now, I’m in the process of writing my methodology.  At this point, I feel like what I’m really doing trying to outline the current practices in social media research, explaining how they are done and giving examples.  Once that is done, I can justify using a population study as the analysis process to help answer my research question and then go into a bit more depth regarding that.  Outlining the available methods seems important because the processes can be a bit different than traditional sociology methods.  Or at least, it feels that way.  This will be updated as I go along.  How often that happens depends on my motivation to write.

Methodology

When conducting social media research, there are ten general methods that can be used to gather and analyze data.  These are:

1. Individual case studies for how a business uses social media and the web,
2. Search and traffic analytics analysis,
3. Sentiment analysis and reputation management,
4. Content analysis,
5. Usability studies,
6. Interaction and collaboration analysis,
7. Relationship analysis to try to determine how people interact and to identify key influencers, and
8. Population studies
9. Online target analysis of behavior and psychographics,
10. Predictive analysis.

Each of these methods offers insights into various aspects of the web and its population.  The type of analysis used is often specific to the purpose of the research, involved blended approaches from traditional analysis types, and different methods are often used in conjunction with each other.  These methods often blend quantitative and qualitative analysis.  Choosing the correct method of gathering analyzing data can be one of the biggest hurdles for being able to measure ROI and understand how a community works.
This section will provide a brief summary of each type, explain how to conduct this type of research and give examples that used that methodology.

Predictive analysis
A search on 13 July 2010 on SPORTDiscus had three results for “predictive analysis.” A search on the same date on Scopus had 605 results, 275 of which were in engineering, 132 in computer science and 102 in medicine. Predictive analysis is probably one of the least used analysis methods, especially in social media and fandom.
What is predictive analysis?  At its simplest, it is identifying a future event or events, monitoring selection actions that precede the event and seeing if those events can be used to predict the outcome of similar events in the future.  If a predictive value is found, an organization can monitor behaviors to help make more informed decisions.
An example of this type of research is “Predicting the Future With Social Media” by Asur and Huberman (2010).  Their goal was to determine if tweet volume and sentiment on Twitter prior to a movie being released could be used to predict how well a movie performs at the box office.  Their methodology involved identifying movie wider release dates that took place on a Friday, creating a list of keyword searches related to those movies, and using the Twitter API to collect all tweets and aggregate date that mention those keywords over a three month time period.  The authors then compared the tweet volume to box office performance.  They concluded that social media “can be used to build a powerful model for predicting movie box-office revenue.” (Asur & Huberman, 2010)
This type of research can be used in conjunction with other methods.  It can be used along side a population study to see if certain actions will result in demographic changes.

References

Asur, S., & Huberman, B. A. (2010). Predicting the Future With Social Media. Social Computing Lab. Retrieved from http://www.hpl.hp.com/research/scl/papers/socialmedia/socialmedia.pdf



Related Posts:

  • http://profiles.yahoo.com/u/ANYPWFYQMNG7NRB55Q7C3PR6C4 Adelaide La Blanche-Dupont

    I think the more predictable something is, the more likely prediction analysis will be used.

    Also if there is a high stake in the outcome.

    What is the difference between 6 and 7, please? Because “interactions' and “relationships” seem similar to me.

  • http://www.fanhistory.com LauraH

    You need a study though to determine if something is predictive. :) I could do a study to find out if total weekly before game post totals for all mailing lists dedicated to an AFL team were for predicting on field success. (Given the level of inactivity, with only I think one or two active lists, I don't think it would be predictive and would be pretty close to random.) If you can prove that there is predictive value, then you could better monetize for that or see if you can't influence those metrics to help you reach a goal.

    One example: Let's hypothesize that there is a strong correlation between the tweet volume Monday to Friday for and AFL team and their at game attendance on Saturday or Sunday. If you were an AFL team and knew that, you could use that knowledge to try to create conversations with fans, try to get media attention which will generate interest on Twitter, get players more engaged… If that volume is predictive and you increase it, then you can increase your at the match attendance and improve your bottom line.

    If the opposite is true, or if the predictive value is higher for Facebook chatter than Twitter chatter, you might move your interaction over there. If you have few resources (as most Aussie teams are not Real Madrid), then this can help you figure out how to best utilize your limited ones.

    Relationship analysis: You and I both follow each other on Twitter. I also have a mutual follow relationship with Jimmy Wales and Ben Parr. You are followed by Harry O'Brien and the Collingwood Football Club's head coach. If you can establish who people have relationships with, you can try to leverage them to get your message to a targeted audience. Using this fake example, I might aim content at you so that you'll tweet about it and get the attention of the Collingwood coach. That could help me accomplish my goal of improving my contacts at the AFL. If you wanted Jimmy Wales to speak at a conference you were putting on, you might try to leverage my relationship with him (which doesn't exist) to accomplish that.

    Interaction and collaboration are less about those relationships and more about actions. How do people work together on a wiki? What does it take to get some one to comment on a post? How do you improve the ratio of reading a post to commenting on a post?

    Does that make sense?

  • http://profiles.yahoo.com/u/ANYPWFYQMNG7NRB55Q7C3PR6C4 Adelaide La Blanche-Dupont

    No, most Aussie teams are not Real Madrid! :-) .

    Malthouse and some of the players of Collingwood got on to Twitter. I don't know what's happening to Nathan Buckley, he will be the coach soon.

    Happy trails for Collingwood vs St Kilda this week! (in fact, probably tonight!)

  • http://profiles.yahoo.com/u/ANYPWFYQMNG7NRB55Q7C3PR6C4 Adelaide La Blanche-Dupont

    And I really appreciated and understood the explanation about relationships and interactions.

    The last two questions under “interaction” are pretty important.

    “What does it take to get some one to comment on a post?”

    “How do you improve the ratio of reading a post to commenting on a post?”

blog comments powered by Disqus