克索瑞波的單心宅

此篇文章轉錄自Science Daily（點此連結）；文章主要論述：能以藉由電腦程式去計算部落格或線上的文字，分析書寫者的心理狀態，協助篩選出是否有憂鬱傾向。針對某些特殊詞彙去做計算書寫者的使用字頻，已是可行且成熟的技術，只是，這是否即是代表書寫者的情緒，仍然根基於一個預設是「文本能代表書寫者本身」（很多憂鬱症患者出書或創作，的確是可以讀到其憂鬱情緒的）；文章提及，電腦軟體只能進行初步篩選，無法取代專業人員對精神疾患的判斷。熱愛科技的台灣，是否會引進這套技術對全台灣的部落客做「精神篩檢」呢？或者更進一步，要求像「莒光作文簿」，把每篇學生週記變成電子檔去計算學生的憂鬱傾向？人類，能否擁有憂鬱且不受篩選、治療的自由？

Computer Program Detects Depression in Bloggers' Texts

ScienceDaily (June 21, 2010) — Researchers at Ben-Gurion University of the Negev (BGU) developed a software program that can detect depression in blogs and online texts. The software is capable of identifying language that can indicate the writer's psychological state, which could serve as a screening tool.

The software, developed by a team headed by Associate Professor Yair Neuman in BGU's Department of Education, was used to scan more than 300,000 English language blogs that were posted to mental health Web sites. The program identified what it perceived to be the 100 "most depressed" and 100 "least depressed" bloggers. A panel of four clinical psychologists reviewed the samples, and concluded that there was a 78 percent correlation between the computer's findings and the panel's.

Professor Yair Neuman will be presenting his BGU team's work at the 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agency Technology in Toronto, Canada, August 31 -- Sept. 3, 2010. Prof. Neuman's findings will also be published in the conference's proceedings.

"The software program was designed to find depressive content hidden in language that did not mention the obvious terms like "depression" or suicide," explains Prof. Neuman. "A psychologist knows how to spot various emotional states through intuition. Here, we have a program that does this methodically through the innovative use of 'web intelligence.'"

For example, the program spots words that express various emotions, like colors that the writer employs to metaphorically describe certain situations. Words like "black" combined with other terms that describe symptoms of depression, such as sleep deprivation or loneliness, will be recognized by the software as "depressive" texts.

Originally conducted for academic purposes, the findings could potentially be used to screen for would-be suicides.

The software provides a screening process that raises an individual's awareness of his or her condition, enables mental health workers to identify individuals in need of treatment, and can then recommend they seek professional help. Because, "no one can actually replace excellent human judgment," says Neuman.

In the United States, there is a big problem of undiagnosed people suffering from depression. The usual screening process is an online questionnaire, which is a self-selective process. If a person is completing a survey, he already suspects a problem. With this software, it is possible to analyze proactively. If the blogger agrees, he will know whether or not he needs to seek professional counseling.