Automatically Categorizing Software Technologies

Informal language and the absence of a standard taxonomy for software technologies make it difficult to reliably analyze technology trends on discussion forums and other on-line venues. We propose an automated approach called <inline-formula><tex-math notation="LaTeX">$\mathrm{Witt}$</tex-math><alternatives><mml:math><mml:mi> Witt </mml:mi></mml:math><inline-graphic xlink:href="nassif-ieq1-2836450.gif"/></alternatives></inline-formula> for the categorization of software technologies (an expanded version of the hypernym discovery problem). <inline-formula><tex-math notation="LaTeX">$\mathrm{Witt}$</tex-math><alternatives><mml:math><mml:mi> Witt </mml:mi></mml:math><inline-graphic xlink:href="nassif-ieq2-2836450.gif"/></alternatives></inline-formula> takes as input a phrase describing a software technology or concept and returns a general category that describes it (e.g., integrated development environment), along with attributes that further qualify it (commercial, php, etc.). By extension, the approach enables the dynamic creation of lists of all technologies of a given type (e.g., web application frameworks). Our approach relies on Stack Overflow and Wikipedia, and involves numerous original domain adaptations and a new solution to the problem of normalizing automatically-detected hypernyms. We compared <inline-formula><tex-math notation="LaTeX">$\mathrm{Witt}$</tex-math><alternatives><mml:math><mml:mi> Witt </mml:mi></mml:math><inline-graphic xlink:href="nassif-ieq3-2836450.gif"/></alternatives></inline-formula> with six independent taxonomy tools and found that, when applied to software terms, <inline-formula><tex-math notation="LaTeX">$\mathrm{Witt}$</tex-math><alternatives><mml:math><mml:mi> Witt </mml:mi></mml:math><inline-graphic xlink:href="nassif-ieq4-2836450.gif"/></alternatives></inline-formula> demonstrated better coverage than all evaluated alternative solutions, without a corresponding degradation in false positive rate.