Why jargon breaks e-commerce search engines

Gary Mersham
3 min readFeb 11, 2022

Research by Baymard Institute has found that in the top 50 grossing US e-commerce sites “A whopping 70% of the search engines are unable to return relevant results for product type synonyms — requiring users to search using the exact same jargon as the site” (my emphasis).

The key finding from a human communication science point view is the focus on jargon.

In human to human and human to machine communication, jargon, like any other message content is encoded by the communicator and decoded by the recipient (see model below) — but what is encoded (in this case a human search query entry) is not accurately decoded by the recipient (a search engine on an e-commerce site). Result: no sale.

A graphical, heuristic metamodel of communication. Source: Mersham and Viviers, 2007

Jargon is terminology commonly understood by people in a certain group, a kind of “insider” language. It may be technical terminology or the characteristic idiom of a special activity or group. It may be social, cultural, political, or scientific or industry specific as the following statements exemplify: He is going to HODL, she only speaks Afrikaans, they are members of the PLO, I love your angiosperms. Scientists claim to use jargon to be precise but a word or phrase loses or changes meaning when you use it with people who aren’t in that specific field or the science.

Jargon is the specific type of language used by a particular group or profession. Jargon can be used to technically describe something or it can be overly technical, obscure, and pretentious in a negative way.

Synonyms top the list for difficult to achieve. Source: Store Pro https://bit.ly/3gzwaA4

Of course, like all language, jargon can cross these usage boundaries, entering into general speech such as “endemic” and “asymptomatic”, or vice versa and given insider meanings in a particular field eg, (a ‘cookie’ and ‘hamburger menu’ in online marketing).
Baymard Institute research showed that on the website of one of the largest consumer electronics e-retailers, a search for “beer cooler” returned more than 500 relevant results, but a search for “beer chiller” delivered not even one.
Let’s bring this closer to home. Esky was an Australian brand of portable cooler but “esky” is also commonly used in Australia to generically refer to portable coolers or ice boxes and is part of the Australian vernacular, replacing “cooler” or “cooler box” and here in New Zealand we call them “chilly bins”. Try finding them on your favourite overseas-based e-commerce site.
As technology journalist of Computerworld points out, these limitations result in most e-commerce site operators to optimizing for the highest-volume queries and effectively ignoring the 70% of requests that constitute the “long tail” of search terms that are rarely used.

That is not the case with a Google or Bing search and the experience is quite different. The difference is “vector search,” a technology rooted in artificial intelligence research that represents information as numbers rather than text bringing the promise of machines understanding jargon much closer.

--

--