In today’s wired world, search engines have changed the way people find data, and social searches are making it even easier to find exactly what you’re looking for, with a little help from your friends. For example, a recent part­ner­ship between Face­book and Microsoft enables Face­book users searching on Microsoft’s Bing to see their friends’ faces in the search results next to web pages their friends have “liked” and shared online.

Jay Aslam, pro­fessor in the Col­lege of Com­puter and Infor­ma­tion Sci­ence at North­eastern Uni­ver­sity, explains how search engines have evolved from simple data­bases into the speedy, sophis­ti­cated and per­son­al­ized rec­om­men­da­tion sys­tems we rely on today.

How have search engines evolved since their inception?

Infor­ma­tion retrieval sys­tems have been around for quite some time, pre­dating the web itself by decades. How­ever, the ear­liest infor­ma­tion retrieval sys­tems relied almost entirely on “on page” infor­ma­tion — that is, the words and other fea­tures present within a doc­u­ment itself — to deter­mine the rel­e­vance of that doc­u­ment to a user query. Modern web search engines, on the other hand, leverage a great deal of “off page” infor­ma­tion as well, such as the hyper­link struc­ture of the web graph, the “anchor text” infor­ma­tion asso­ci­ated with the link from one web page to another, and “click through” data that search engines col­lect about the web pages that users actu­ally visit when pre­sented with a list of web pages in response to a query, to name but a few impor­tant examples.

How will the new form of per­son­al­ized social search affect the way we interact and retrieve infor­ma­tion? Will other search engines adopt the social search func­tion, and what future trends can we expect to see in search engines?

Many search engines are now lever­aging con­text to help deter­mine the results returned to users. That con­text may be tem­poral — a search for “hol­iday recipes” may well return dif­ferent results at Thanks­giving than at Christmas — and/​or spa­tial — a search for “movie show­times” may well return dif­ferent results in San Fran­cisco than in Boston. Per­son­al­iza­tion is another form of con­text: search results may depend on the iden­tity of the user, such as her past search and browsing behavior.

Per­son­al­ized social search is yet another example, where search results may depend on one’s social circle. This may well have an impact, espe­cially for searches related to rec­om­men­da­tions: prod­ucts, restau­rants, movies and so forth. Rec­om­men­da­tion sys­tems such as those employed by Net­flix and Amazon have proven quite suc­cessful, and these sys­tems effec­tively make rec­om­men­da­tions based on the tastes of anony­mous users whose pro­files “match” the given cus­tomer. Rec­om­men­da­tions effec­tively made from known friends may well be more trusted, if not more accurate.

Was a social net­work part­ner­ship with a major search engine inevitable?

Cer­tainly the part­ner­ship between Face­book and Bing makes sense, and was per­haps inevitable given their mutual com­pe­ti­tion with Google.

What is your take on any poten­tial pri­vacy or secu­rity issues that might arise?

Under­standing and con­trol­ling one’s pri­vacy on the web is dif­fi­cult. The recent con­tro­versy with Facebook’s pri­vacy policy is but one example, as are per­son­al­ized retar­geted ads that “follow” one through cyber­space. Having one’s rec­om­men­da­tions “pushed” to others only adds to this mix.

View selected pub­li­ca­tions of Jay Aslam in IRis, Northeastern’s dig­ital archive.