Thoughts on the Utility of Seminars...

Everyone who's involved in academia probably has some angst about seminars. At the very least, it's always difficult to figure out which talks to attend when you feel like you already don't have enough time to take care of the work that you have to do. I've seen quite a few seminars at this point, and as the years have gone by, I think I've become more conflicted about them than ever.

I think that there are obviously many 'purposes' behind seminars. For instance, an invited speaker from another institution can tell you about interesting work that, if not directly relevant to your own projects, could at the very least be 'inspirational'. Regardless of whether you're happy with attending seminars for interest's sake (I've done it many times myself and would encourage it whenever possible), I think that there is a way that many of these talks could be made far more likely to be helpful. I also think that this is where my conflict regarding seminars lies:

I don't understand academic seminars that are primarily focused on 'results' rather than methods. Of course we're all excited about telling people about interesting new results, but on top of being fundamental to the practice of science, I think it's often more interesting to learn how those results were obtained.

Some people are probably reading this thinking that I'm crazy: of course people tell you how they obtained their results! While in some fields I think that this is true, I've been surprised by how often in large, complex dataset genomics, people gloss over the important details of analyses. In fact, often people will give the most cursory statement about how a figure was produced, ignoring complicating factors such as which subset of a larger dataset is actually being shown. 

I'm most shocked by presentations of a genre that I've affectionately come to label the 'dump truck' method of presentation. This is the situation where someone plasters each slide with an extremely complex, poorly-labelled figure and basically asks you to take their word for the fact that it's revealing some amazingly novel aspect of biology. The few times that I've seen extremely egregious versions of this form of talk, the only thing that ran through my head was that the speaker really wanted to convince us that they were doing an amazing amount of work... somehow1.

Perhaps I'm naïve or simply missing something fundamental about how seminars 'work', but I get far more out of talks that are as much about how something was determined rather as they are about what was determined in the first place. This is particularly true in the case of 'informal' seminar series, such as meetings among labs interested in the same topic. In many results-focused seminars, I'd rather that the speaker had presented half of the 'neato' things they'd done, if it meant getting a better picture of how such things were done.

Remember, nullius in verba.

1I've received the advice from a few people that this is a particularly bad way to approach a job talk - yet I've seen in done a few times now.