Voter decision support system

Voter decision support systems are software systems designed to support voters in gathering relevant information, evaluating that information and deciding between alternatives.
Voter decision support systems are decision-making software, decision support systems and intelligent decision support systems, integrating components including, but not limited to: search, multimedia search, recommendation, aggregation, summarization, multi-document summarization, clustering, note-taking, knowledge sharing and data visualization.
Types of content pertinent to voter decision support systems include: content from the websites of political parties and candidates, news articles, interviews, panel discussions, debates, debate coverage and analysis, fact-checking, editorials, letters to the editor, expert content (e.g. content from scientists, historians, economists, foreign policy experts) and encyclopedia articles.
Data for visualization and presentation include that from: journalistic organizations, scientific organizations, universities, open government data and Wikidata.
Decision support systems
A decision support system is a software system which supports individual or organizational decision-making activities.
The history of decision support systems traces back to the middle of the 1960s and the concepts and technologies are still evolving. Historically, there are five types of decision support systems to consider: communication-driven, data-driven, document-driven, knowledge-driven and model-driven. Communication-driven decision support systems provide users with the ability to communicate, collaborate and share knowledge with one another. Data-driven decision support systems provide users with the ability to access, manipulate and visualize data. Document-driven decision support systems provide users with the ability to search and retrieve documents and multimedia. Knowledge-driven decision support systems provide users with the ability to access and utilize structured knowledge, inference engines, reasoning systems, automated reasoning and expert systems. Model-driven decision support systems provide users with the ability to access and utilize statistical, financial, economic, optimization and simulation models. Voter decision support systems can draw upon a number of these approaches simultaneously.
In 2005, Scott P. Robertson indicated that a voter-centered perspective should be adopted for the design of systems that support information gathering, organizing and sharing, deliberation, decision-making, and voting.
Intelligent decision support systems
An intelligent decision support system is a decision support system which makes extensive use of artificial intelligence techniques.
Expert systems
Intelligent decision support systems have made use of expert systems. Expert systems are knowledge-based systems, software systems which reason and use knowledge bases to make decisions or solve complex problems. In addition to uses in intelligent decision support systems, expert systems have been utilized in the applications of: interpretation, prediction, diagnosis, design, planning, monitoring, debugging, repair, instruction and control.
Historically, there are six types of expert systems to consider: rule-based, frame-based, hybrid, model-based, ready-made and real-time expert systems. A rule-based expert system represents knowledge as a series of rules. A frame-based expert system represents knowledge as frames. A hybrid expert system represents knowledge in multiple ways simultaneously. A model-based expert system is structured around the use of one or more models. Ready-made expert systems are mass-produced; there are two types of ready-made expert systems, those for general use and those which are industry- or product-specific. A real-time expert system always produces a response in an allocated amount of time.
Machine learning
Machine learning is a useful technology for decision support systems. Machine learning is a field of artificial intelligence which uses statistical techniques to give computer systems the ability to “learn” (e.g. to progressively improve performance on a specific task) from data, without being explicitly programmed. Machine learning techniques utilized with decision support systems include: artificial neural networks, evolutionary algorithms, decision tree learning, support vector machines, case-based reasoning, Bayes learning and pattern recognition.
Dialogue systems
Intelligent decision support systems can support natural-language, conversational and multimodal user interfaces.
Discussion
Workflow
Workflows can describe processes and procedures for information seeking and decision-making using voter decision support systems.
Users of workflow-enhanced voter decision support systems can create, view, edit, configure, share and synchronize workflows and activity diagrams. Activity diagrams are visual, diagrammatic representations of workflows. Such visual diagrams facilitate diagrammatic reasoning and promote one's ability to grasp and to make sense of information rapidly and readily. Activity diagrams, decision maps or decision-making diagrams can provide structured, semi-formal frameworks for representing information seeking and decision-making processes and procedures using interactive visual language.
As users progress through structured processes and procedures, contexts can be provided to other system components, for instance facilitating contextual search and recommendation.
Arguments, justifications and rationale for decisions can be interactively or automatically generated for decisions resulting from the use of structured processes and procedures for information seeking and decision-making.
Intelligent layout
News design and page layout algorithms can compose screens and user experiences with content from multiple content providers. Users can express preferences with respect to which content providers to utilize as well as with respect to how content should be sorted. Intelligent layout algorithms should take users’ preferences into consideration while helping users to avoid filter bubbles and echo chambers.
Note-taking
Users can make notes for later use. Users can make notes between elections for use during elections.
Knowledge sharing
Users can share notes and other content with one another.
Argument technology
Utilizing computational linguistics, natural language processing, text analysis and argument mining, argument technology can detect spin, opinion and persuasion and can analyze and measure the quality of arguments. So doing can convenience users as they compose content and as they review content from one other, including in dialogical contexts. In addition to Web services, such functionalities can be provided through the plugin architectures of word processor software or those of Web browsers. Internet forums, for instance, can be greatly enhanced by such software tools and services.
Users of argumentation-enhanced voter decision support systems can create, view, edit, configure, share and synchronize arguments and argument maps. Argument maps are visual, diagrammatic representations of arguments. Such visual diagrams facilitate diagrammatic reasoning and promote one's ability to grasp and to make sense of information rapidly and readily. Argument maps can provide structured, semi-formal frameworks for representing arguments using interactive visual language.
Argument technology can help users to avoid filter bubbles and echo chambers as it can discover disagreements within sets of content so that users can be provided with navigation to content which disagrees with items from recommender systems.
Printing and displaying results
Users can print their decision-making results or display them on their mobile devices, taking printouts or their mobile devices into polling locations.
Privacy
By utilizing technologies such as Solid, voter decision support systems can be designed which protect users’ privacy.

Main Menu

See Also

Main Menu