Gilbert, assistant professor in the School of Interactive Computing, focused his attention on the \u201cEnron corpus,\u201d a body of 500,000 emails among about 150 former Enron employees, making it the largest email dataset available for public study. Even after taking a \u201cconservative, careful\u201d approach\u2014applying numerous filters and eliminating thousands of emails that would have muddied his conclusions\u2014he still was able to identify lists of words that reliably predicted whether emails traveled up or down the ladder.<\/p>\n \u201cAcross a wide variety of messages and relationships, these phrases consistently stand out as signaling a power relationship between two people,\u201d Gilbert said. \u201cThe probability of it occurring due to chance alone is less than 1 in 1,000.\u201d<\/p>\n Primarily Gilbert\u2019s work could be applied in designing \u201csmarter\u201d email software<\/strong>. Future email clients, he said, might be able to differentiate between emails sent from superiors or subordinates, and then use that information to better address someone\u2019s email preferences. Post-5 p.m. messages from people under you, for example, might get held for delivery until the next day, while emails from the boss\u2014or the boss\u2019 assistant\u2014could go right through.<\/p>\n \u201cWe have organizational charts, but they don\u2019t tell the whole story,\u201d said Gilbert, adding that the research could help map \u201cinformal power and reporting structures\u201d in an organization. \u201cA classic example is the CEO\u2019s administrative assistant: That person may not occupy a high box on the org chart, but he or she still has a large amount of influence.\u201d<\/p>\n Top 5 Upward Predictors Top 5 Downward Predictors The project falls in the research field called \u201capplied natural language processing,\u201d which has been an important subfield of artificial intelligence for the past 25 years. Tools first developed in the area, however, can be applied to other data and yield enlightening results about human interaction through electronic media or simply how people relate to each other.<\/p>\n One complicating factor in Gilbert\u2019s research was the dataset itself. Aside from its utility as grist for study, the Enron corpus can also be considered profoundly flawed as an example of \u201cnatural\u201d language; after all, Enron and its officers were responsible for one of the largest, most systemic examples of corporate fraud in U.S. history, and Gilbert acknowledges that the behavior behind this ignominy likely bled into communications among Enron officers. To minimize the chance that their statistical findings captured phenomena unique to Enron, Gilbert and his team manually went through the emails and removed phrases that appeared specific to the company. They also threw out all correspondence after Enron\u2019s bad behavior had come to light.<\/p>\n \u201cThe trick,\u201d he said, \u201cwas to find a point just before things really started to fall apart. We chose a date (May 1, 2001) several months before a formal investigation of Enron began and before its executives started selling off their own Enron stock. For all the emails that preceded that date, it\u2019s reasonable to assume that Enron and its people behaved just like any other large private entity.\u201d<\/p>\n Gilbert\u2019s research will be presented today at the 2012 ACM Conference on Computer Supported Cooperative Work (CSCW), being held Feb. 11-15 in Seattle. Gilbert said CSCW, now in its 15th year, is widely regarded as the first conference devoted to social computing.<\/p>\n To view the full 100-word lists that reliably predict hierarchical direction, read Gilbert\u2019s paper located here<\/a>. And about that certain four-letter word that rhymes with hit?<\/p>\n \u201cYeah, I don\u2019t know what the story on the cursing is,\u201d Gilbert said. \u201cMaybe that\u2019s the next paper.\u201d<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":" From the Georgia Tech College of Computing press release via Newswise: Members of the modern workforce might be surprised to learn that if they use the word \u201cweekend\u201d in a… Read more »<\/a><\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[8],"tags":[188,58,12,102],"_links":{"self":[{"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/posts\/1323"}],"collection":[{"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/comments?post=1323"}],"version-history":[{"count":1,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/posts\/1323\/revisions"}],"predecessor-version":[{"id":1324,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/posts\/1323\/revisions\/1324"}],"wp:attachment":[{"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/media?parent=1323"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/categories?post=1323"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/therapytoronto.ca\/news\/wp-json\/wp\/v2\/tags?post=1323"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}![\"\"](\"http:\/\/therapytoronto.ca\/images\/blogpics\/Email.jpg\" "\\"email\\"")
Members of the modern workforce might be surprised to learn that if they use the word \u201cweekend\u201d in a workplace email, chances are they\u2019re sending the message up the org chart. The same is true for the words \u201cvoicemail,\u201d \u201cdriving,\u201d \u201cokay\u201d\u2014and even a choice four-letter word that rhymes with \u201chit.\u201d However a new study by Georgia Tech\u2019s Eric Gilbert shows that certain words and phrases indeed are reliable indicators of whether workplace emails are sent to someone higher or lower in the corporate hierarchy.<\/strong><\/p>\n
\n\u2022 the ability to
\n\u2022 I took
\n\u2022 are available
\n\u2022 kitchen
\n\u2022 thought you would<\/p>\n
\n\u2022 have you been
\n\u2022 you gave
\n\u2022 we are in
\n\u2022 title
\n\u2022 need in<\/p>\n