Search results

The term knowledge refers to the part of the world investigated by a specific discipline and that includes a specific taxonomy, vocabulary, concepts, theories, research methods and standards of justification. Our approach uses domain knowledge to improve the quality of business process models (BPMs) by exploiting the domain knowledge provided by large language models (LLMs). Among these models, ChatGPT stands out as a notable example of an LLM capable of providing in-depth domain knowledge. The lack of coverage presents a limitation in each approach, as it hinders the ability to fully capture and represent the domain’s knowledge. To solve such limitations, we aim to exploit GPT-3.5 knowledge. Our approach does not ask GPT-3.5 to create a visual representation; instead, it needs to suggest missing concepts, thus helping the modeler improve his/her model. The GPT-3.5 may need to refine its suggestions based on feedback from the modeler.

We initiate our semantic quality enhancement process of a BPM by first extracting crucial elements including pools, lanes, activities and artifacts, along with their corresponding relationships such as lanes being associated with pools, activities belonging to each lane and artifacts associated with each activity. These data are systematically gathered and structured into ArrayLists, a form of organized collection that allows for efficient data manipulation and retrieval. Once we have this structured data, our methodology involves creating a series of prompts based on each data element. We adopt three approaches to prompting: zero-shot, few-shot and chain of thoughts (CoT) prompts. Each type of prompting is specifically designed to interact with the OpenAI language model in a unique way, aiming to elicit a diverse array of suggestions. As we apply these prompting techniques, the OpenAI model processes each prompt and returns a list of suggestions tailored to that specific element of the BPM. Our approach operates independently of any specific notation and offers semi-automation, allowing modelers to select from a range of suggested options.

This study demonstrates the significant potential of prompt engineering techniques in enhancing the semantic quality of BPMs when integrated with LLMs like ChatGPT. Our analysis of model activity richness and model artifact richness across different prompt techniques and input configurations reveals that carefully tailored prompts can lead to more complete BPMs. This research is a step forward for further exploration into the optimization of LLMs in BPM development.

The limitation is the domain ontology that we are relying on to evaluate the semantic completeness of the new BPM. In our future work, the modeler will have the option to ask for synonyms, hyponyms, hypernyms or keywords. This feature will facilitate the replacement of existing concepts to improve not only the completeness of the BPM but also the clarity and specificity of concepts in BPMs.

To demonstrate our methodology, we take the “Hospitalization” process as an illustrative example. In the scope of our research, we have presented a select set of instructions pertinent to the “chain of thought” and “few-shot prompting.” Due to constraints in presentation and the extensive nature of the instructions, we have not included every detail within the body of this paper. However, they can be found in the previous GitHub link. Two appendices are given at the end. Appendix 1 describes the different prompt instructions. Appendix 2 presents the application of the instructions in our example.

In our research, we rely on the domain application knowledge provided by ChatGPT-3 to enhance the semantic quality of BPMs. Typically, the semantic quality of BPMs may suffer due to the modeler's lack of domain knowledge. To address this issue, our approach employs three prompt engineering methods designed to extract accurate domain knowledge. By utilizing these methods, we can identify and propose missing concepts, such as activities and artifacts. This not only ensures a more comprehensive representation of the business process but also contributes to the overall improvement of the model's semantic quality, leading to more effective and accurate business process management.

The purpose of this study was to investigate whether including an Islamic appeal in a culture-neutral product advertisement has a positive effect on consumer attitudes to the advertisement leading to higher purchase intentions while considering religious affiliation and religiosity as moderating factors of the relationship.

Conditional process analysis was applied to examine the mediation of the relationship between ad version and purchase intention through attitude to the advertisement as well as the moderating role of religious affiliation and religiosity among 819 consumers within the Dubai market.

The analysis in this paper revealed that including an Islamic appeal in an advertisement does not have a positive effect on attitude to the advertisement or purchase intention, neither for Muslim consumers in general nor for Muslim consumers with high levels of religiosity. Conversely, including an Islamic appeal has a significant negative effect on the purchase intentions of Christian consumers within the Dubai market, as well as on those consumers who did not state their religious affiliation.

Marketers should reconsider the use of Islamic appeals in product advertising, especially in relation to the promotion of culture-free products within diverse expatriate populations such as that represented by the Emirate of Dubai.

This study sheds light on the underexplored role of religious affiliation and religiosity in relationship to consumer behavior within the field of Islamic marketing in a major retail hub in the Middle East.

The purpose of this study is to investigate the moderation effects of religiosity in the relationship between service quality (SQ), customer satisfaction (CS), relationship quality (RQ) and Islamic banking (IB) loyalty in a non-Islamic country.

This study used a quantitative approach and a cross-sectional research design. The data was collected by a closed-ended questionnaire from a systematic sample of 267 customers of full-fledged Islamic banks in Tanzania. Structural equation modeling and regression analysis techniques were used to analyze the data.

Results indicate that religiosity is a significant (p < 0.05) moderator of the relationship between SQ and loyalty (β = 0.176), and between CS and loyalty (β = 0.263). However, religiosity sharpens the impact of CS on loyalty (β increases from 0.170 to 0.263, p < 0.05) and does not sharpen the impact of SQ on loyalty (β decreases from 0.338 to 0.176, p < 0.05). The results further indicate that religiosity is not a significant moderator (p > 0.05) in the link between RQ and loyalty (β = −0.112).

This study used only full-fledged Islamic banks in Tanzania. Therefore, future research could be undertaken by including conventional banks that have introduced an IB window.

To build and maintain a loyal customer base, Islamic banks should take advantage of religiosity by providing a wide range of Sharia-based products and services that truly distinguish them from conventional banks. Accordingly, policymakers should establish an appropriate legal framework to enable Islamic banks to leverage religiosity to sharpen the impact of CS on loyalty and hence maintain loyalty in non-Islamic countries like Tanzania.

This study proposes and validates the theoretical model of loyalty in IB by showing the role of religiosity as a moderator in a non-Islamic country. This knowledge strengthens the overall understanding of loyalty in IB. To the best of the authors’ knowledge, this study is the first to examine the moderation effects of religiosity in the link between RQ and loyalty, and thus between SQ, CS, RQ and loyalty in a single study.