Publications

Here you can find publications, press releases, and other downloads about the GCA.

You would like to get in touch with us? Write to us at info[at]green-consumption-assistant.de

Research Articles

Article „Credible and easily available sustainability information in internet searches on Ecosia” in the anthology „Consumer Social Responsibility in the digital space”

In chapter 7 of the anthology Corporate Social Responsibility in the Digital Space, an article on the GCA has been published. Marja Lena Hoffmann, Maike Gossen and Nina Güldenpenning present the green consumption assistant as a potential solution for the information complexity of sustainable consumption decisions.

The anthology aims to collect current German-language research on ConSR in the digital space and to open a suitable discourse space on different, interdisciplinary perspectives. It addresses questions such as how shared or joint responsibility can be understood in the digital context in the first place, what effects the digitalization of consumption has on the information and sanctioning potential of consumers, and what roles digital decision architectures and the expansion of consumption action options are able in this context.

Article: Driving Sustainable Behavior with Persuasive Technology

In the article published by Maike Gossen and Patricia Jankowski, crucial design elements are identified. It is about refining the system and evaluating its effectiveness in changing users‘ behaviour. The evaluation is operationalised through the Persuasive System Design (PSD) model.

 

Gossen, Maike, Jankowski, Patricia (2022): Driving Sustainable Behavior with Persuasive Technology: The Green Consumption Assistant. Ökologisches Wirtschaften, 2.2022 (37), p.12-13.

Nudging Sustainable Consumption: A Large-Scale Data Analysis of Sustainability Labels for Fashion in German Online Retail

Labelling The publication addresses the question of how online retailers use sustainability pledges to inform consumers about the sustainability of products. In a study, an large data set with sustainability information on almost 17,000 fashion products of the leading online retailers in Germany were examined. The results show that many fashion products are labelled as sustainable, with two-thirds of the products using their label and one-third using a label verified by a third party. Only 14 percent of labelled products have trustworthy, third-party verified sustainability labels. This low percentage makes it difficult for consumers to understand the scope of a product’s sustainability. Moreover, the heterogeneity of labels can confuse consumers and make them feel unsure.

The practical recommendations are given in the publication support policy initiatives that address the risk of greenwashing through uncertified and insufficient sustainability information.

GreenDB: Toward a Product-by-Product Sustainability Database

One aim of our project is to build an AI-based product database that enables the development of a recommendation assistant. This paper explains how scraping technologies can be used to request publicly available data about products and information about their sustainability, and how this information can be integrated into a central database. Furthermore, the first version of the GreenDB is presented and published.

Paper in "Frontiers in Big Data"

Paper: A Benchmark for Data Imputation Methods

Improving the data quality of applications that use machine learning (ML) helps to increase their performance and enables the use of more efficient models. One of the most common problems of data quality is missing values. In this peer-reviewed article, Sebastian Jäger, Arndt Allhorn, and Felix Bießmann evaluated different methods based on different data sets that can be used to predict these missing values, which we encounter again and again with regard to sustainable product recommendations. Finally, recommendations are made for a wide variety of situations based on the results of our experiments.

Abstract

With the increasing importance and complexity of data pipelines, data quality became one of the key challenges in modern software applications. The importance of data quality has been recognized beyond the field of data engineering and database management systems (DBMSs). Also, for machine learning (ML) applications, high data quality standards are crucial to ensure robust predictive performance and responsible usage of automated decision making. One of the most frequent data quality problems is missing values. Incomplete datasets can break data pipelines and can have a devastating impact on downstream ML applications when not detected. While statisticians and, more recently, ML researchers have introduced a variety of approaches to impute missing values, comprehensive benchmarks comparing classical and modern imputation approaches under fair and realistic conditions are underrepresented. Here, we aim to fill this gap. We conduct a comprehensive suite of experiments on a large number of datasets with heterogeneous data and realistic missingness conditions, comparing both novel deep learning approaches and classical ML imputation methods when either only test or train and test data are affected by missing data. Each imputation method is evaluated regarding the imputation quality and the impact imputation has on a downstream ML task. Our results provide valuable insights into the performance of a variety of imputation methods under realistic conditions. We hope that our results help researchers and engineers to guide their data preprocessing method selection for automated data quality improvement.

Working Paper

Arbeitspapier #07 Sustainability Tips, Eco-Quiz or AI-powered Chat?

In dem letzten Arbeitspapier der Green Consumption Assistant- Reihe untersucht das Team die Wirkung verschiedener Nachhaltigkeits-Interventionen in der Suchmaschine Ecosia auf potenzielle Verhaltensänderungen. Verschiedene Prototypen wie Nachhaltigkeitstipps, Quizzes und ein AI-Chat wurden dafür in einem Fokusgruppen-Experiment vorgeführt und Reaktionen ausgewertet.

Abstrakt:

Nutzer*innen von Ecosia wünschen sich bei der Informationssuche und Nutzung der grünen Suchmaschine Orientierungshilfe für einen nachhaltigen Lebensstil. Dafür ist es wichtig, den Informationsbedarf verschiedener Nutzer*innengruppen in Bezug auf Nachhaltigkeit besser zu verstehen, um überzeugende umweltbezogene Suchmaschinenfunktionen zu entwickeln. In dem Projekt Green Consumption Assistant haben wir daher eine qualitative Studie durchgeführt und untersucht, wie Nutzer*innen verschiedene Interventionen zur Verhaltensänderung der Suchmaschine wahrnehmen. Wir untersuchen drei Funktionen (Nachhaltigkeitstipps, Öko-Quiz und KI-gestützter Chat) und diskutieren die Prototypen mit insgesamt sechs Online-Fokusgruppen, die jeweils aus Personen mit unterschiedlichem nachhaltigkeitsorientiertem Hintergrund („Umweltbewusstseinstypen“) zusammengesetzt sind. Nach der Durchführung von Inhalts- und Stimmungsanalysen zeigen die Ergebnisse, dass die Wahrnehmung der Funktionen von der Präsentation der Funktion sowie von individuellen Faktoren wie dem Umweltbewusstsein abhängt. Die Nachhaltigkeitstipps wurden sowohl von Ecosia-Nutzer*innen als auch von den Aufgeschlossenen, Skeptischen und Unentschlossenen positiv aufgenommen. Der KI-gestützte Chat führte zu polarisierenden Diskussionen und wurde von Aufgeschlossenen, Konsequenten und Unentschlossenen als attraktiv empfunden. Umgekehrt fanden nur Aufgeschlossene und Ecosia-Nutzer:innen das Öko-Quiz attraktiv. Die qualitative Studie unterstreicht die Bedeutung der Segmentierung von Nutzer*innen und der Zielgruppenansprache zur Verbesserung der Wirksamkeit von Maßnahmen zur Verhaltensänderung. Die Studie regt an, die getesteten Prototypen auf Ecosia zu verbessern und bietet Einblicke in die Nachhaltigkeitsinformationsbedürfnisse unterschiedlicher Nutzer*innengruppen.

DOI: https://doi.org/10.14279/depositonce-20020

Working Paper: Sustainable Product Recommendations – Identification and Evaluation of Sustainable Products

In this publication, Marja Lena Hoffmann deals with sustainability labels and comparable sustainability indicators that the Green Consumption Assistant uses to evaluate sustainable products. The working paper points out conceptual considerations as well as methodological weaknesses that are relevant for the further development of the Green Consumption Assistant.

Abstract

The production, use and disposal of products have a significant impact on people and the environment. Consumers are interested in buying sustainable products, but often feel overwhelmed in identifying them and assessing their environmental and social impacts. Concerns about greenwashing can unsettle consumers too. At the same time, e-commerce has expanded rapidly. As a result, the influence of online platforms such as search engines, price comparison sites and online marketplaces on consumer decisions has also increased. These developments entail opportunities as well as risks for sustainable consumption. The interdisciplinary research project „Green Consumption Assistant” (GCA) addresses how sustainable consumption can be promoted in online environments. With the aim of facilitating sustainable purchasing decisions, data on sustainable products is recorded and evaluated automatically in a database. Based on that, clothing and electronics products identified as sustainable are labelled in the search engine Ecosia. The selection of products displayed is based on sustainability labels and comparable sustainability indicators assigned by reliable third-party providers. This working paper describes the current approach for identifying and evaluating sustainable products, the underlying conceptual considerations, methodological weaknesses, and potential for further development.

Working Paper: Climate Pledge Rating – A hands-on Evaluation and Visualization of Companies’ Responses to Climate Change

In this publication, Marja Lena Hoffmann focuses on the Climate Pledge Rating, which was developed and implemented as part of the Green Consumption Assistant (GCA). The rating shows Ecosia users reviews and ratings of sustainability pledges of selected companies. This is intended to support users in making sustainable consumption decisions.

Abstract

The climate crisis is already causing heat waves, floods, droughts, and many more severe impacts on earth. As outlined by the Sixth Assessment Report of the Intergovernmental Panel on Climate Change (IPCC) drastic action is necessary to reduce greenhouse gas (GHG) emissions and limit the global temperature increase to 1.5 °C. This requires halving global GHG emissions by 2030 and reaching net-zero emissions by 2050. To reach this goal, governments, individuals, and the private sector need to take immediate action. In recent years, many companies have come forward with net-zero pledges and carbon reduction targets. However, understanding those pledges and evaluating whether they are ambitious and credible or mainly PR tools is challenging and can be misleading. One initiative attempting to increase the transparency of companies’ climate pledges is the Climate Pledge Rating, which was developed and implemented within the Green Consumption Assistant (GCA), a joint project by the Technical University of Berlin, the Berliner Hochschule für Technik, and the green search engine Ecosia. The rating shows evaluations and ratings of pledges from selected companies to users of Ecosia. Thereby, it reduces the information complexity of pledges and informs users about the ambition behind the companies’ climate commitment and what those would mean for achieving the goal to keep the global temperature from rising beyond 1.5 °C.

Arbeitspapier #3: Climate Pledge Rating – A hands-on Evaluation and Visualization of Companies’ Responses to Climate Change

In dieser Veröffentlichung beschäftigt sich Marja Lena Hoffmann mit dem Climate Pledge Rating, das im Rahmen des Green Consumption Assistant (GCA) entwickelt und umgesetzt wurde. Das Rating zeigt Nutzer*innen von Ecosia Bewertungen und Einstufungen von Nachhaltigkeitsversprechen ausgewählter Unternehmen an. Das soll Nutzer*innen unterstützen, nachhaltige Konsumentscheidungen zu treffen.

Abstrakt
Die Klimakrise verursacht bereits Hitzewellen, Überschwemmungen, Dürren und viele weitere schwerwiegende Auswirkungen auf der Erde. Wie im sechsten Bericht des Intergovernmental Panel on Climate Change (IPCC) dargelegt, sind drastische Maßnahmen erforderlich, um die Treibhausgasemissionen zu verringern und den globalen Temperaturanstieg auf 1,5 °C zu begrenzen. Dies erfordert eine Halbierung der globalen Treibhausgasemissionen bis 2030 und das Erreichen von Netto-Null-Emissionen bis 2050. Um dieses Ziel zu erreichen, müssen Regierungen, Einzelpersonen und der private Sektor unverzüglich Maßnahmen ergreifen. In den letzten Jahren haben viele Unternehmen Netto-Null-Versprechen und Ziele zur Reduzierung von Kohlenstoffemissionen gemacht. Es ist jedoch schwierig, diese Versprechen zu verstehen und zu beurteilen, ob sie ehrgeizig und glaubwürdig sind oder hauptsächlich PR-Maßnahmen darstellen. Eine Initiative, die versucht, die Transparenz der Klimazusagen von Unternehmen zu erhöhen, ist das Climate Pledge Rating, das im Rahmen des Green Consumption Assistant (GCA), einem gemeinsamen Projekt der Technischen Universität Berlin, der Berliner Hochschule für Technik und der grünen Suchmaschine Ecosia, entwickelt und umgesetzt wurde. Das Rating zeigt den Nutzer*innen von Ecosia Bewertungen und Einstufungen von Versprechen ausgewählter Unternehmen an. Es reduziert damit die Informationskomplexität von Versprechen und informiert die Nutzer*innen darüber, welche Ambitionen hinter den Klimaversprechen der Unternehmen stehen und was diese für das Erreichen des Ziels, die globale Temperatur nicht über 1,5 °C ansteigen zu lassen, bedeuten würden.
DOI: https://doi.org/10.14279/depositonce-18624

Working Paper: Climate Pledge Rating – A hands-on Evaluation and Visualization of Companies’ Responses to Climate Change

In this publication Marja Lena Hoffmann focuses on the Climate Pledge Rating, which was developed and implemented within the Green Consumption Assistant (GCA). The rating shows evaluations and ratings of pledges from selected companies to users of Ecosia. This is supposed to support users in making sustainable consumption decisions.

Abstract

The climate crisis is already causing heat waves, floods, droughts, and many more severe impacts on earth. As outlined by the Sixth Assessment Report of the Intergovernmental Panel on Climate Change (IPCC) drastic action is necessary to reduce greenhouse gas (GHG) emissions and limit the global temperature increase to 1.5 °C. This requires halving global GHG emissions by 2030 and reaching net-zero emissions by 2050. To reach this goal, governments, individuals, and the private sector need to take immediate action. In recent years, many companies have come forward with net-zero pledges and carbon reduction targets. However, understanding those pledges and evaluating whether they are ambitious and credible or mainly PR tools is challenging and can be misleading. One initiative attempting to increase the transparency of companies’ climate pledges is the Climate Pledge Rating, which was developed and implemented within the Green Consumption Assistant (GCA), a joint project by the Technical University of Berlin, the Berliner Hochschule für Technik, and the green search engine Ecosia. The rating shows evaluations and ratings of pledges from selected companies to users of Ecosia. Thereby, it reduces the information complexity of pledges and informs users about the ambition behind the companies’ climate commitment and what those would mean for achieving the goal to keep the global temperature from rising beyond 1.5 °C.

GCA Working Paper II – Driving Forces of Green Shopping Behavior

In our second publication, Robin Jadkowski looks at psychological determinants that lead to more eco-friendly purchasing decisions. This involves developing a method that matches user tracking data from our GCA with survey data and investigating the relationship of different variables to each other that could intensify eco-friendly behaviour.

Abstract

This study evaluates psychological and socio-demographic driving forces of pro-environmental behavior (PEB) in an online shopping environment. Previous empirical studies substantiate the role and strengths of numerous psychological driving forces that influence individual PEB. However, the type of PEB operationalization is heterogenous, as well as the type and operationalization of the driving forces. Steg & Vlek (2009) stress the point that effective interventions have to be aimed at these driving forces and that the strengths and relationship differs for specific types of PEB. Up to date, studies that use actual behavior as operationalizations of PEB in online shopping environments are rare, therefore this study pursued two main goals: (1) Test a method to link user tracking data of a digital shopping assistant (as indicators for pro-environmental shopping decisions) with self-reported survey items; (2) Exploratively assess the relationship of four socio-demographic and 14 psychological variables that may act as driving forces for PEB. The click behavior of N = 35 beta users of an online shopping assistant was tracked over a period of five months and successfully linked to previously obtained survey data. It was not possible to reliably detect effects of the assessed driving forces – PEB relationship with the achieved sample size. In conclusion, this studies procedure revealed great potential for future research to evaluate the effects of psychological variables on PEB in a real shopping environment.

GCA Working Paper I – Scaling Sustainability Advice

We are proud to publish the first working paper for the Green Consumption Assistant project. In this paper, our colleague Cathérine Lehmann summarises our decision-making processes for sustainable product recommendations, as well as possible approaches for scaling up.

Abstract

Data availability on the sustainability of products is low which poses challenges for actors from all sectors dealing with promoting sustainable consumption. We describe how we currently provide users of a Chrome browser extension with general sustainability advice and with recommendations of best-in-class products in terms of sustainability. Then we outline a possible concept towards more automatisation and thus scalability of the current approach. For the latter, we discuss six different schemes for generating large-scale green recommendations on a product level, finding that currently product sustainability can be best evaluated in terms of data availability when resorting to lists of labelled products. In the future, Product Environmental Footprints and similar data should be more easily available in order to have quantifiable data for research and for showing more information to users. Overall, an integrated approach, including e.g. aspects of  organizational sustainability, might help to fill data voids and/or to provide a more complete picture of a product’s sustainability level.

Blog Posts

Article at RESET „Greenwashing in Online Fashion: Consumers are Being Deceived by Sustainability Claims”

In the contribution to RESET – Digital for Good, Maike Gossen and Felix Biessmann problematise the extent of sustainability labels that customers are confronted with during online shopping. Using the GreenDB database, the GCA research team investigated how trustworthy the available sustainability information is in Germany’s largest online shops. The results show that only a small percentage of products labelled as sustainable meet the high standards of credibility and sustainability.

The full article „Nudging Green Consumption: A Large-Scale Data Analysis of Sustainability Labels for Fashion in German Online Retail“ by Maike Gossen, Felix Bießmann.

Article at Klimareporter° „Net zero promise without any ambition”

Since the Paris Climate Conference, hundreds of companies have published ‘Net Zero Pledges’ in which they show how they intend to contribute to climate protection. In order to make the ambitions behind these pledges transparent, the TU Berlin has developed the Climate Pledge Rating together with the search engine Ecosia. In the article at Klimareporter°, Marja Lena Hoffmann and Maike Gossen report that the amounts to fight the climate crisis, expressed through Net Zero Pledges, are not far-reaching enough and demonstrate how the Climate Pledge Rating shows this.

Article at RESET „Climate Pledges by Companies are not Ambitious Enough”

Since the Paris Climate Conference, hundreds of companies have published ‘Net Zero Pledges’ in which they show how they intend to contribute to climate protection. In order to make the ambitions behind these pledges transparent, the TU Berlin has developed the Climate Pledge Rating together with the search engine Ecosia. In the article at RESET – Digital for Good, Marja Lena Hoffmann and Maike Gossen report that the amounts to fight the climate crisis, expressed through Net Zero Pledges, are not far-reaching enough and demonstrate how the Climate Pledge Rating shows this.

Article at BNW „What contribution are promises of climate neutrality making to the transformation of the economy?”

Since the Paris Climate Conference, hundreds of companies have published ‘Net Zero Pledges’ in which they show how they intend to contribute to climate protection. In order to make the ambitions behind these pledges transparent, the TU Berlin has developed the Climate Pledge Rating together with the search engine Ecosia. In the article at Bundesverband Nachhaltige Wirtschaft e.V. (BNW), Marja Lena Hoffmann and Maike Gossen report that the amounts to fight the climate crisis, expressed through Net Zero Pledges, are not far-reaching enough and demonstrate how the Climate Pledge Rating shows this.

KI-Berlin

03.06.2021 Article in KI-Berlin Blog

In the article titled „Using Artificial Intelligence to make more sustainable behaviour easy for people” #KI-Berlin introduces the GCA to the broader public and describes how our first iteration works.

Interviews