Person: Valogianni, Konstantina
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
First Name
Konstantina
Last Name
Valogianni
Affiliation
IE University
School
IE Business School
Department
Information Systems and Technology
Identifiers
Name
6 results
Search Results
Now showing 1 - 6 of 6
Publication Autonomous Prompt Engineering in Large Language Models(Cornell University, 2024-06-25) Valogianni, Konstantina; Kepel, Daan; OpenAI Researcher Access Program; https://ror.org/02jjdwm75Prompt engineering is a crucial yet challenging task for optimizing the performance of large language models (LLMs) on customized tasks. This pioneering research introduces the Automatic Prompt Engineering Toolbox (APET), which enables GPT-4 to autonomously apply prompt engineering techniques. By leveraging sophisticated strategies such as Expert Prompting, Chain of Thought, and Tree of Thoughts, APET empowers GPT-4 to dynamically optimize prompts, resulting in substantial improvements in tasks like Word Sorting (4.4% increase) and Geometric Shapes (6.8% increase). Despite encountering challenges in complex tasks such as Checkmate in One (-14.8%), these findings demonstrate the transformative potential of APET in automating complex prompt optimization processes without the use of external data. Overall, this research represents a significant leap in AI development, presenting a robust framework for future innovations in autonomous AI systems and highlighting the ability of GPT-4 to bring prompt engineering theory to practice. It establishes a foundation for enhancing performance in complex task performance and broadening the practical applications of these techniques in real-world scenarios.Publication Sustainability Awareness and Smart Meter Privacy Concerns: The cases of US and Germany(IE University, 2022-02-01) Schallehn, Frauke; Valogianni, Konstantina; https://ror.org/02jjdwm75We investigate public awareness about sustainability, e-mobility and smart meters in Germany and the US, two countries leading the e-mobility development, but with different sustainability policies. By applying sentiment analysis and Natural Language Processing on tweets from the two countries over the last decade (2010 to end of 2019), we found that the sustainability awareness in Germany is higher than the US. We see that the US is at an earlier sustainability maturity state, creating fertile grounds for establishing sustainability policies on time to shape public opinion. Furthermore, we find that after the introduction of the Sustainable Development Goals (SDGs) in 2015, the overall awareness in both countries has increased, showing the potential of such policies. In addition, in contrast to expectations, we see that the smart meter privacy concerns have recently started to deteriorate, possibly as a result of governmental efforts to educate the public about smart meter technology. Finally, we see that the German public tweets more positively about e-mobility, compared to the US, whereas the content of e-mobility discussions differs: Germany is more concerned about e-mobility adoption, whereas the US is more focused on battery efficiency and other technological developments associated with e-mobility.Publication Causal ABMs: Learning Plausible Causal Models using Agent-based Modeling(SSRN, 2022-08-15) Valogianni, Konstantina; Padmanabhan, Balaji; Qiu, Liangfei; https://ror.org/02jjdwm75We present Causal ABM, a methodology to derive causal structures describing complex underlying behavioral phenomena. Agent-based models (ABMs) have powerful advantages for causal modeling that have not been explored sufficiently. Unlike traditional causal estimation approaches which often result in “one best” causal structure that is learned, two properties of ABMs - equifinality (the ability of different sets of conditions or model representations to yield the same outcome) and mutlifinality (the same ABM might yield different outcomes) - can be exploited to learn multiple diverse “plausible causal models” from data. Using an illustrative example of news sharing on social networks we show how this idea can be applied to learn such causal sets. We also show how genetic algorithms can be used as a estimation technique to learn multiple plausible causal models from data due to their parallel search structure. However, significant computational challenges remain before this can be generally applied, and we, therefore, highlight specific key issues that need to be addressed in future work.Publication Online social games: The effect of social comparison elements on continuance behaviour(Elsevier, 2021-04-01) Esteves, José; Greenhill, Anita; Valogianni, Konstantina; https://ror.org/02jjdwm75Online social games, played within social networks or games requiring social interaction with peers, are revolutionizing the nature of video-games due to their social aspect and the ability of users to compare their performance with their friends or people in their network. Social comparison features, such as leaderboards, individual scores, achievement badges and level maps, are commonly used in online games to enforce the social interaction of players. However, one of the biggest challenges that the social game industry is currently facing is the ability to increase user enjoyment, and keep its players engaged in the games. To probe more deeply into whether and how players’ continuance intention is influenced by social comparison processes, we combine two theoretical lenses: social comparison theory and self-efficacy theory. We conducted real-world data collection to measure the impact of social comparisons in player perceived enjoyment, online social gaming self-efficacy and game continuance. The results indicate that upward identification and downward contrast are the most influential comparison elements in game continuance. The results of these two comparisons have significant implications for both the theoretical application of social comparison in online settings and for the practical implications of future game design.Publication Information Systems Research for Smart Sustainable Mobility: A Framework and Call for Action(Informs, 2023-09-03) Ketter, Wolfgang; Schroer, Karsten; Valogianni, Konstantina; https://ror.org/02jjdwm75Transportation is a backbone of modern globalized societies. It also causes approximately one third of all European Union and U.S. greenhouse gas emissions, represents a major health hazard for global populations, and poses significant economic costs (e.g., due to traffic congestion). However, rapid innovation in vehicle technology, mobile connectivity, computing hardware, and artificial intelligence–powered information systems heralds a deep socio-technical transformation of the sector. The emergence of connected, autonomous, shared, and electric vehicle technology has created a digital layer that resides on top of the traditional physical mobility system. The resulting layered modular architecture is similar to that seen in other cyber-physical systems. Yet, it also comes with several characteristics and challenges that are unique to the domain of mobility and require entirely new solution approaches. Although other management and domain-specific research disciplines have started to embrace the new opportunities for research resulting from this deep structural change, the information systems (IS) community’s involvement in smart mobility research has been marginal. Yet, we argue that our field’s uniquely multidisciplinary, data-driven, and socio-technical research lens puts it in a strong position to address many of the large-scale societal challenges encountered in the mobility sector. Therefore, we make the case for IS research to play an active role in delivering a smart sustainable mobility ecosystem that is beneficial to users, mobility providers and the environment. We contribute a research framework to direct IS research efforts while providing a shared understanding of the smart sustainable mobility domain. We also present seven IS research opportunities along the dimensions of this framework and propose concrete angles of attack which we hope will spur an impactful and structured research agenda in the area.Publication Sustainable Electric Vehicle Charging using Adaptive Pricing(Wiley, 2020-03-13) Ketter, Wolfgang; Collins, John; Zhdanov, Dmitry; Valogianni, Konstantina; https://ror.org/02jjdwm75A transition to electric vehicles (EVs) is widely assumed to be an important step along the road to environmental sustainability. However, large-scale adoption of EVs may put electricity grids under critical strain, since peaks in electricity demand are likely to increase radically. Efforts to manage demand peaks through pricing schemes may create new peaks at low-price periods, if large numbers of EV owners use smart charging to benefit from low prices. This effect is expected to be amplified when EV owners adopt smart decision support to assist them with optimal charging decisions. Therefore, energy policymakers are interested in advanced pricing schemes that can smooth demand or induce demand that comes as close as possible to a desired profile. We show, through simulations calibrated with real-world data, that current approaches to electricity pricing are limited in their ability to induce desired demand profiles. To address this challenge, we present adaptive pricing, a method to learn from EV owner reactions to prices and adjust announced prices accordingly. Our method draws on the Green Information Systems principles and can assist grid operators in ensuring the reliable operation of the grid. We evaluate our results in simulations, where we find that adaptive pricing outperforms current electricity pricing schemes, yielding results close to the theoretically optimal ones. We test our method in inducing both flat and extremely volatile demand profiles, and we see that in both cases it manages to induce EV charging close to the ideal scenario under perfect information.