In this article a social constructionist approach to information technology (IT) literacy is introduced. This approach contributes to the literature on IT literacy by introducing the concept of IT self as a description of the momentary, context-dependent, and multilayered nature of interpretations of IT competencies. In the research literature, IT literacy is often defined as sets of basic skills to be learned, and competencies to be demonstrated. In line with this approach, research on IT competencies conventionally develops models for explaining user acceptance, and for measuring computer-related attitudes and skills. The assumption is that computer-related attitudes and self-efficacy impact IT adoption and success in computer use. Computer self-efficacy measures are, however, often based on self-assessments that measure interpretations of skills rather than performance in practice. An analysis of empirical interview data in which academic researchers discuss their relationships with computers and IT competence shows how a self-assessment such as "computer anxiety" presented in one discussion context can in another discussion context be consigned to the past in favor of a different and more positive version. Here it is argued that descriptions of IT competencies and computer-related attitudes are dialogic social constructs and closely tied with more general implicit understandings of the nature of technical artifacts and technical knowledge. These implicit theories and assumptions are rarely taken under scrutiny in discussions of IT literacy yet they have profound implications for the aims and methods in teaching computer skills.
