Efthimios Bothos

Using Social Media to Predict Future Events with Agent-Based Markets

Agents can exploit user-generated content available in social media by extracting user sentiments and assessments and using them to make informed transactions on the market.

Collective intelligence for idea management with Internet‐based information aggregation markets

Purpose – The purpose of this paper is to explore the use of information aggregation markets (IAMs) for community‐based idea management and to present IDeM, a novel Internet‐based software tool that can be used for generating and evaluating new ideas utilizing the concept of IAMs.Design/methodology/approach – Starting with a review of existing methods for collective intelligence, IAMs are identified as a prominent method for collective intelligence. Specific requirements for exploring IAMs for idea management are derived. Based on these requirements, a software tool for implementing IAMs in the context of idea management is developed (IDeM). IDeM has been evaluated and evaluation results are used to identify IDeMs benefits and limitations. A review of related work points out the innovative characteristics of IDeM.Findings – Evaluation results indicate that IAMs is an efficient method for idea generation and evaluation. Moreover IDeM is perceived both as easy to use and efficient in supporting idea genera...

IDEM: A Prediction Market for Idea Management

Collaborative systems and methods are used within corporate environments to support innovation and management of new ideas. The aggregation of innovation-related information from a community of users is a non-trivial task that requires the use of specialized collaborative systems and methods. In this paper we explore the use of Prediction Markets for community-based idea management and present IDEM, a software system that is used for generating and evaluating new ideas utilizing the concept of Prediction Markets. In addition to trading, IDEM supports users submit new ideas, rate and comment on them. Academic experiments and industrial pilots reveal the perceived usefulness of the system.

Information market based recommender systems fusion

Recommender Systems have emerged as a way to tackle the overload of information reflected in the increasing volume of information artefacts in the web and elsewhere. Recommender Systems analyse existing information on the user activities in order to estimate future preferences. However, in real life situations, different types of information can be found and their interpretation can vary as well. Each recommender system implements a different approach for utilizing the known information and predicting the user preferences. A problem is that of blending the recommendations in an adaptive, intuitive way while performing better than base recommenders. In this work we propose an approach based on information markets for the fusion of recommender systems. Information Markets have unique characteristics that make them suitable building blocks for ensemble recommenders. We evaluate our approach with the Movielens and Netflix datasets and discuss the results of our experiments.

Exploring the Links Between Persuasion, Personality and Mobility Types in Personalized Mobility Applications

Recent approaches on tackling the problem of sustainable transportation involve persuasive systems and applications. These systems focus on changing citizens’ behavior towards adopting transportation habits that rely more on the use of public transportation, bicycles and walking and less on private cars. A main drawback of existing applications is the limited use or lack of personalization aspects that consider differences in users’ susceptibility to persuasive strategies. In this paper, we explore two user traits that can be used for personalizing the persuasive strategies applied to end users: personality and mobility type. More specifically, we present the results of a study where we examined the perceived persuadability of eight persuasive strategies on users of five personality types and three mobility types.

Choice architecture for environmentally sustainable urban mobility

Personal transportation greatly contributes to environmental pollution from CO2 emissions and persuasive technologies could assist travellers in reducing their ecological impact. In this work we focus on the design of persuasive travel recommenders in order to support travellers, who have a pre-existing interest in taking action to lessen their impact on the environment, adopt green transportation habits. Our approach examines recommender systems under a choice architecture framework and aims at providing urban travellers with a personalized travel recommender that helps them plan routes while considering the environmentally friendliest travel modes.

Idea selection and Information Aggregation Markets

Several methods and software tools exist for evaluating new ideas in corporate environments, which provide significant help to decision makers when selecting the most promising suggestions for innovation. In this paper, we identify five criteria for assessing idea evaluation methods (number and type of ideas, number and motivation of evaluators, type of feedback) and we use them to review prominent methods (multi-criteria analysis, statistical analysis, qualitative research, rapid prototyping, feasibility studies and Information Aggregation Markets). We identify Information Aggregation Markets as a prominent new method and we present a novel system that implements the concept of Information Aggregation Markets as well as early results from its evaluation.

Leveraging User Inspiration with Microblogging-Driven Exploratory Search

In creative tasks, the user expects to acquire holistic information, to explore the space of available information and to come up with diverse views before converging to a solution for the creative task. We hypothesize that the implicit use of social chatter in information seeking activities can enhance the potential for novel, diverse and unexpected encounters which can in turn inspire users. We present an interactive exploratory search tool that combines diversification of content and sources with a user interface design that visualises cues from the social chatter generated with microblogging services such as Twitter and lets users interactively explore the available information space. A task-based user study comparing our system to a query-based baseline indicates that our system significantly improves inspirational discoveries by providing access to more interesting, novel and unexpected information.

Using Individual and Collaborative Challenges in Behavior Change Support Systems: Findings from a Two-Month Field Trial of a Trip Planner Application

Besides other popular strategies, such as feedback and (social) comparisons, challenges have been proposed and used to influence people’s behavior towards a targeted goal. However, only very limited data on the effectiveness of such approaches and how to best design them is available yet. In this work we report the findings of a two months field study analyzing the effectiveness and perception of challenges in the context of influencing personal mobility. Individual and collaborative approaches towards challenges were studied, and specific focus was laid on what aspect makes users willing to participate in these challenges. Our findings suggest that both individual and collaborative challenges have the potential to sustain the interest of users in using behavior change support systems, that collaborative and individual challenges seem to not attract different types of users, that individual challenges in general are preferred, and that challenges are only a useful means for a subset of users. Also, ICT-competence seems to be an important aspect of being willing to participate in electronically organized challenges.

Creative user centric inspirational search

The demo paper describes the Creative User Centric Inspirational Search, which aims to leverage user inspiration in information seeking activities. CRUISE is an interactive exploratory search tool that combines diversification of content and sources with a user interface design that visualizes cues from the social chatter generated with microblogging services such as Twitter and lets users interactively explore the available information space. The tool is based on the observation that users often use the social chatter to follow links and initiate information seeking activities which can lead to unexpected discoveries which can in turn inspire them.