AI for the evaluation of participation? The potential of language models to recognise modes of transport in participation contributions

In this article in the journal Internationales Verkehrswesen, Laura Mark, Julia Romberg and Tobias Escher present a language model that can be used to reliably recognise modes of transport in participation contributions. They show that supervised machine learning can usefully support the evaluation of participation contributions in mobility-related online participation processes.

Summary

Consultations are an important part of transport planning and can help to integrate knowledge from the public into the planning process. However, online formats in particular often result in large volumes of contributions, the thorough evaluation of which is resource-intensive. It is hoped that the use of AI will support this.

The language model presented in this article is based on the concept of supervised machine learning for text classification. Pre-trained models are re-fined using smaller data sets. In this way, a model can be adapted to a specific area of application, such as mobility-related consultation processes.

A pre-trained German-language version of the high-performance RoBERTa language model was used as a starting point. Using a categorisation scheme that mainly distinguishes between the modes of transport mentioned, 1,700 contributions from seven transport planning consultation processes were manually coded. The resulting data was used partly as training data for fine-tuning the language model and partly for evaluation.

Results

  • Overall, it was shown that language models already available today are suitable for supporting the evaluation of consultation processes in practice. The language model developed here for recognising the modes of transport can serve as the basis for a specific application in municipal planning practice.
  • The post-trained RoBERTa language model is very effective at assigning the appropriate modes of transport. The model presented by us can always reliably assign well over 90% of the entries correctly to the modes of transport they contain.
  • For the processes on whose contributions the model had been trained, an average of 97% of the categories could be correctly assigned (on a separate test set). For contributions from other transport-related participation procedures, the appropriate modes of transport could still be assigned very reliably with an accuracy of 91 to 94%.
  • The performance of the model therefore hardly deteriorates when it is applied to previously unknown data from mobility-related participation procedures. This means that manual coding in advance can be omitted, at least for similarly structured participation procedures, which significantly reduces the effort involved.

Publication

Mark, Laura; Romberg, Julia; Escher, Tobias (2024): KI zur Auswertung von Beteiligung. In: Internationales Verkehrswesen 76 (1), S. 12–16.

The political shaping of the sustainability transformation: participatory and ecological?

In this article in regierungsforschung.de, the academic online magazine of the NRW School of Governance, Tobias Escher explores the question of whether the participation formats required for a participatory development of the transformation to a more sustainable society can also be implemented in an ecologically sustainable manner. In other words, the question is how the principle of (ecologically) sustainable governance can be upheld in the democratically important area of political participation.

Abstract

The transformation to a sustainable society can only succeed through the involvement of all stakeholders. At the same time, sustainable governance requires that these participation processes also fulfil the requirements of sustainability. Based on a systematic discussion of the greenhouse gas emissions generated by various political participation formats, this article argues that in view of the functional and normative significance of political participation, its environmental footprint does usually not contradict the demand for sustainable governance.

Key findings

  • The implementation of participation formats generates greenhouse gas emissions due to the energy required, the mobility of the participants and, where applicable, catering and accommodation. Crucially, the level of emissions depends on whether the formats are held in person or digitally (see table below).
  • For local face-to-face formats, the emissions from the event venue and mobility of participants are comparatively low and only amount to around 2kg of CO2-equivalents per person in the scenario analysed. The emissions increase considerably as soon as participants have to travel further (using fossil-fuelled transport) – in the underlying scenario by a factor of twelve to 24kg. This is roughly equivalent to the average emissions from a 100km car journey.
  • In contrast, online participation formats only generate very low emissions (around 0.3kg per person in the scenario). Nevertheless, the choice of participation formats cannot be based solely on their short-term ecological costs, but must also take into account normative requirements for inclusion and popular control. Digital participation formats in particular represent significant barriers to participation for already disadvantaged population groups (see also our DigiBeSt-report).
  • Overall, participation has an ecological footprint, but this is generally justified by functional and normative considerations because after all, governance should not only be sustainable, but above all democratic!
face-to-face participationdigital participation
local(inter)-regionalasynchronsynchron
energyheating & climatisation of event venueoperation of end user devices & data centresmore data intensive communication
mobilitytraveltravelnot applicable
catering & accommodationcateringaccommodationnot applicable
Direct environmental impact of different participation formats. The darker the colour, the greater the respective emissions from this source. The emissions generally increase with the number of participants and the duration of the participation format.

Publication

Escher, Tobias (2024): Die politische Gestaltung der Nachhaltigkeitstransformation: partizipativ und ökologisch? Essay. In: Regierungsforschung.de (15. Jahrgang). https://regierungsforschung.de/die-politische-gestaltung-der-nachhaltigkeitstransformation-partizipativ-und-oekologisch/

Pushback for the municipal mobility transition? Joint closing event of SÖF Junior Research Groups CIMT and MoveMe

The two junior research groups in Social-Ecological Research CIMT and MoveMe are holding a joint final event showcasing some results of their research into the transition to sustainable mobility. The event is scheduled to take place online on 26. April 2024. More information is available in German.

Inclusivity, transparency and policy effects – procedural justice through participation?

In a presentation at the annual congress of AESOP (Assosiation of European Schools of Planning) in 2023, Katharina Holec, Laura Mark and Tobias Escher presented results from a consultative participation procedure. Key question was whether the procedure could contribute to procedural justice.

Summary

Consultative participation is a frequently used tool to correct traditional inequalities in planning. It is often used to negotiate conflicts relevant to everyday life. Citizens are encouraged to express their interests and ideas. In addition, local administrations expect an increase in legitimacy beliefs among citizens through including them into processes. Procedural justice can be seen as an important aspect of the desired increase in acceptance. The underrepresentation of certain socio-economic groups in the input of consultative participation is one of the main challenges for procedural justice.

Our example is one of the case studies, which we have accompanied scientifically over the last years. Using a mixed methods we investigate the contribution that the procedure makes to procedural justice. We conceptualize this describing the relevance of the aspects inclusivity, transparency and policy effects of a consultative procedure.

Although inclusivity was the declared goal of the organizers it is hardly achieved in the input of the process – that is, in the question of who participates. Things look somewhat more positive when observing the throughput. Discussions were well organized and were also perceived positively by citizens. If we look at the evaluation of the transparency of the process itself, i.e. the throughput, the participants rated it positively. There are limitations in the evaluation of the transparency of the result and the communication after the process. A policy effect exists and is primarily perceived by the participants. However, the policy effect is limited to non-essential issues of the process.

Key findings

  • While the consultation process was organized aiming at an overrepresentation of specific marginalized groups, it fails to include lower educated and non-male individuals. The assessment of throughput inclusivity is more positive.
  • The consultation process was carried out with timely publication of the results of the individual procedural steps and is also perceived as transparent overall with few differences between different social groups. People with disabilities are somewhat more critical. The assessment of the transparency of the results is somewhat more negative.
  • Effects on political decision-making can be found in the fact that the process strengthened and supported the progressive ideas of the administration. Influences of participation existed but were mainly relevant for specific issues, such as the location of bike paths or bus stops not a general direction.
  • These effects are more strongly perceived by participants.

Annotation and Provision of Datasets

As part of our project, we worked on the manual annotation of a large number of datasets with the aim of supporting the development of AI methods for evaluating public participation contributions.

Supervised machine learning requires training datasets in order to learn patterns related to the respective codings. In the area of citizen participation, there is a lack of comprehensively coded German-language datasets. In order to meet this need, we have therefore worked on annotating German-language participation processes from the field of mobility according to four dimensions:

  • Firstly, we have thematically classified contributions according to modes of transportation, other requirements for public space, and defects that need to be fixed immediately.
  • Second, we coded processes by argumentative sentences and divided them into premises and conclusions.
  • Thirdly, we have assigned argumentative units of meaning to how concrete they are.
  • Fourthly, we have coded textual location information.

A more detailed description of the datasets – as of June 2022 – can be found in our publication: Romberg, Julia; Mark, Laura; Escher, Tobias (2022, June). A Corpus of German Citizen Contributions in Mobility Planning: Supporting Evaluation Through Multidimensional Classification. Since then, we have continued to work on the thematic coding of the datasets and revised our scheme of modes of transport.

The following table shows the current status of annotation and is updated on an ongoing basis (in German):

In accordance with our open source policy, the annotated datasets are made available to the public under Creative Commons CC BY-SA License when possible.

A number of publications have been produced based on these data sets. These can be found at https://www.cimt-hhu.de/gruppe/romberg/romberg-veroeffentlichungen/.

Master’s thesis on the thematic classification of participation contributions with Active Learning

As part of his Master’s thesis in the MA Computer Science at Heinrich Heine University Düsseldorf, Boris Thome dealt with the classification of participation contributions according to the topics they contain. This thesis continues the work of Julia Romberg and Tobias Escher by examining a finer classification of contributions according to subcategories.

Summary

Political authorities in democratic countries regularly consult the public on specific issues but subsequently evaluating the contributions requires substantial human resources, often leading to inefficiencies and delays in the decision-making process. Among the solutions proposed is to support human analysts by thematically grouping the contributions through automated means.

While supervised machine learning would naturally lend itself to the task of classifying citizens’ proposal according to certain predefined topics, the amount of training data required is often prohibitive given the idiosyncratic nature of most public participation processes. One potential solution to minimize the amount of training data is the use of active learning. In our previous work, we were able to show that active learning can significantly reduce the manual annotation effort for coding top-level categories. In this work, we subsequently investigated whether this advantage is still given when the top-level categories are subdivided into subcategories. A particular challenge arises from the fact that some of the subcategories can be very rare and therefore only cover a few contributions.

In the evaluation of various methods, data from online participation processes in three German cities was used. The results show that the automatic classification of subcategories is significantly more difficult than the classification of the main categories. This is due to the high number of possible subcategories (30 in the dataset under consideration), which are very unevenly distributed. In conclusion, further research is required to find a practical solution for the flexible assignment of subcategories using machine learning.

Publication

Thome, Boris (2022): Thematische Klassifikation von Partizipationsverfahren mit Active Learning. Masterarbeit am Institut für Informatik, Lehrstuhl für Datenbanken und Informationssysteme, der Heinrich-Heine-Universität Düsseldorf. (Download)

Master’s thesis on the automated classification of arguments in participation contributions

As part of her master’s thesis in the MA Computer Science at Heinrich Heine University Düsseldorf, Suzan Padjman dealt with the classification of argumentation components in participation contributions. This thesis continues our team’s previous work by looking at cases in which argumentative sentences can contain both a premise and a conclusion.

Summary

Public participation processes allow citizens to engage in municipal decision-making processes by expressing their opinions on specific issues. Municipalities often only have limited resources to analyze a possibly large amount of textual contributions that need to be evaluated in a timely and detailed manner. Automated support for the evaluation is therefore essential, e.g. to analyze arguments.

When classifying argumentative sentences according to type (here: premise or conclusion), it can happen that one sentence contains several components of an argument. In this case, there is a need for multi-label classification, in which more than one category can be assigned.

To solve this problem, different methods for multi-label classification of argumentation components were compared (SVM, XGBoost, BERT and DistilBERT). The results showed that BERT models can achieve a macro F1 score of up to 0.92. The models exhibit robust performance across different datasets – an important indication of the practical usability of such methods.

Publication

Padjman, Suzan (2022): Mining Argument Components in Public Participation Processes. Masterarbeit am Institut für Informatik, Lehrstuhl für Datenbanken und Informationssysteme, der Heinrich-Heine-Universität Düsseldorf. (Download)

Project work on the automated recognition of locations in participation contributions

As part of her project work in the MA Computer Science at Heinrich Heine University Düsseldorf, Suzan Padjman worked on the development of methods for the automated recognition of textually described location information in participation procedures.

Summary

In the context of the mobility transition, consultative processes are a popular tool for giving citizens the opportunity to represent and contribute their interests and concerns. Especially in the case of mobility-related issues, an important analysis aspect of the collected contributions is which locations (e.g. roads, intersections, cycle paths or footpaths) are problematic and in need of improvement in order to promote sustainable mobility. Automated identification of such locations has the potential to support the resource-intensive manual evaluation.

The aim of this work was therefore to find an automated solution for identifying locations using methods from natural language processing (NLP). For this purpose, a location was defined as the description of a specific place of a proposal, which could be marked on a map. Examples of locations are street names, city districts and clearly assignable places, such as “in the city center” or “at the exit of the main train station”. Pure descriptions without reference to a specific place were not considered as locations. Methodologically, the task was regarded as a sequence labeling task, as locations often consist of several consecutive tokens, so-called word sequences.

A comparison of different models (spaCy NER, GermanBERT, GBERT, dbmdz BERT, GELECTRA, multilingual BERT, multilingual XLM-RoBERTa) on two German-language participation datasets on cycling infrastructure in Bonn and Cologne Ehrenfeld showed that GermanBERT achieves the best results. This model can recognize tokens that are part of a textual location description with a promising macro F1 score of 0.945. In future work, it is planned to convert the recognized text phrases into geocoordinates in order to depict the recognized location of citizens’ proposals on a map.

Publication

Padjman, Suzan (2021): Unterstützung der Auswertung von verkehrsbezogenen Bürger*innenbeteiligungsverfahren durch die automatisierte Erkennung von Verortungen. Projektarbeit am Institut für Informatik, Lehrstuhl für Datenbanken und Informationssysteme, der Heinrich-Heine-Universität Düsseldorf. (Download)

Effects of online citizen participation on legitimacy beliefs

In this article in the journal Policy & Internet, Tobias Escher and Bastian Rottinghaus explore the question of how participation in local consultation processes (on planning of cycling infrastructure) affects attitudes towards local politics. To this end, in 2018 they examined a total of three participation procedures in which the cities of Bonn, Cologne (district Ehrenfeld) and Moers consulted their citizens on local cycling infrastructure. In each case, for five weeks citizens were able to submit, comment on and evaluate proposals through an online platform. In total, more than 3,000 proposals were collected which were to be incorporated into the subsequent cycling planning (see further information on the Cycling Dialogues project).

Abstract

In order to generate legitimacy for policies and political institutions, governments regularly involve citizens in the decision-making process, increasingly so via the Internet. This research investigates if online participation does indeed impact positively on legitimacy beliefs of those citizens engaging with the process, and which particular aspects of the participation process, the individual participants and the local context contribute to these changes. Our surveys of participants in almost identical online consultations in three German municipalities show that the participation process and its expected results have a sizeable effect on satisfaction with local political authorities and local regime performance. While most participants report at least slightly more positive perceptions that are mainly output-oriented, for some engagement with the process leads not to more, but in fact to less legitimacy. We find this to be the case both for those participants who remain silent and for those who participate intensively. Our results also confirm the important role of existing individual resources and context-related attitudes such as trust in and satisfaction with local (not national) politics. Finally, our analysis shows that online participation is able to enable constructive discussion, deliver useful results and attract people who would not have participated offline to engage.

Key findings

  • The participation processes we studied and to which citizens were invited by their respective councils do indeed have an influence on the attitudes of those who participate in such consultations.
  • For many of the participants, the positive effect that was hoped for does indeed occur: they are more positive about the local institutions (mayor, administration) and local politics as a whole. The decisive factor for the assessment is whether one expects local politics to take the citizens’ proposals seriously and act upon them. In other words, the result of the process is more important for attitudes than the process itself.
  • It is noteworthy that this holds true also for those who have rather negative views of local politics to begin with. However, previous experience with local politics also plays a role: those who already have a higher level of satisfaction and trust in the municipality are becoming more positive by participation.
  • At the same time, participation can also lead to less satisfaction. We were able to show this, on the one hand, for those who were intensively involved in the participation process and made a lot of proposals. On average, this group was less satisfied in the end, probably because their expectations of the impact of their efforts were disappointed. Those who did not actively participate but only visited the online procedure without making suggestions themselves were also more dissatisfied. These people were apparently mainly concerned about the fact that the process took place exclusively online.
  • Overall, however, our results show that such online participation processes not only enable constructive participation, but that they also reach additional groups: Almost half of the respondents would not have participated if the process had only been conducted with on-site formats requiring physical presence.

Publication

Escher, Tobias; Rottinghaus, Bastian (2023): Effects of online citizen participation on legitimacy beliefs in local government. Evidence from a comparative study of online participation platforms in three German municipalities. In: Policy & Internet, Artikel poi3.371. DOI: 10.1002/poi3.371.

Mobility transition in practical terms: Perspectives of the SÖF junior research groups with a focus on mobility

On 25 & 26 October the three SÖF junior research groups with a focus on mobility met in Hannover to exchange insight from their current research, identify common themes and discuss possible future opportunities for collaboration.

There is more information available in German.