Bill Curtis

Three Problems Overcome With Behavioral Models Of The Software Development Process

Software development processes are usually modeled by manifestations of the software artifact at given stages in its evolution and the nature of the transformations being applied to it during these stages. Thus, the software process is purported to begin with a stage called something like requirements development, or in some cases with the even the earlier step of a feasibility study. Such models vary the ordering of process stages (eg., prototyping vs. a traditional waterfall vs. incremental building and releasing). Yet, in all such models the software process is bounded by those activities that initiate and terminate the development of a specific software product.

The Psychology of Programming in the Large: Team and Organizational Behaviour

Publisher Summary This chapter focuses on the psychology of programming in relation to team and organizational behavior. Software development must be studied at several behavioural levels. Organizing programmers into teams superimposes a layer of social behavior on the cognitive requirements of programming tasks. Two structures have been proposed for programming teams based on the centralized versus decentralized team organizations often studied in group dynamics research. A hybrid approach to structuring programming teams might be taken on large projects that have characteristics favourable to different types of programming teams. Programming team activities offer many opportunities for peer review activities that may be formal or informal components of the development process. On the other hand, team methodologies must focus on coordinating the tasks and product concept. The structure of programming teams should reflect the nature of the task rather than the organization, allow members to speak as if with one mind, and determine the tasks the team can effectively handle.

HUMAN/COMPUTER INTERACTION IN THE YEAR 2000

The plan of this summary will be to first summarise the main points made during the discussion. My own comments focussed on the important but relatively neglected area of motivation, particularly intrinsic motivation as a factor in the design of Human/Computer interaction. As the work force moves away from farm and manufacturing toward an involvement with service and knowledge, intrinsic motivation, as opposed to extrinsic, will become increasingly important. Partly this is because it is easier to measure performance objectively in farm and manufacturing environments.

Modeling the Software Design Process

There are many levels at which the software development process can be modeled. MCC-STP’s Empirical Studies Team has developed a layered behavioral model to guide our analyses of these processes. We have performed empirical studies of processes at each of these levels. At the level of individual cognitive problem-solving processes, we conducted a thinking aloud protocol study wherein software professionals were given a specification for an elevator system (a lift) and instructed to design a control system for it to the level of detail that they would hand over to a competent programmer for implementation. In this Lift Experiment we were seeking to determine the primary breakdowns experienced during design to determine the functionality that should be explored in developing prototypes of design tools. At the team and project levels, we videotaped three months worth of requirements and design meetings of a project team designing an object server. We analyzed these tapes to determine how group dynamics altered the processes we observed during individual design problem-solving, and what types of design technology should be provided in the group meeting environment. Finally, at the organizational and business milieu levels we conducted on-site interviews with personnel from 17 large software development projects to gather case study information on actual design processes. Transcripts of these interviews were analyzed to model factors affecting the processes of making design decisions and communicating them across the project. In this paper models of the software process developed at each of the levels are described and the aggregation of their effects across levels are discussed.

Panel session on collaborative design: technology futures

Collaborative design is one(of several) appropriate focus for CSCW due to the shear amount and variety of computer-oriented design work being done, its goal oriented nature in a group work setting, and its importance in tommorrows world. Design is a highly creative task typically done well by experts with many years of experience. Similiarities in design activities and problems were seen across disciplines at the 1st MCC Interdisciplinary Design Symposium. Questions raised there in general discussion serve as a platform for more pointed questions raised by empirical study. These might include:

Psychological Research on Software Development

Every psychological study portrays a paradigm, a model of what the investigator believes is really important in human behavior. When the choice of paradigms is unconscious, investigators are often faced with attempting to defend their hypotheses with data which do not bear on the argument. The motley body of psychological studies on programming has been guided by six psychological paradigms: 1) individual differences, 2) group behavior, 3) organizational behavior, 4) human factors, 5) cognitive ergonomics, and 6) cognitive science.