Advancing Human‑Computer Interaction with Natural Language

Processing: Emerging Trends and Applications

Abdul Rasheed P.

, Arunkumar R.

, S. Jagatheeswaran

, Emmanuel S.

and S. K. Lokesh Naik

Department of English, EMEA College of Arts and Science, Kondotty, Kerala, India

Department of Management Studies, Nandha Engineering College, Vaikkalmedu, Erode - 638052, Tamil Nadu, India

Department of Computer Science and Engineering, J.J. College of Engineering and Technology, Tiruchirappalli, Tamil

Nadu, India

New Prince Shri Bhavani College of Engineering and Technology, Chennai, Tamil Nadu, India

Department of Computer Science and Engineering, MLR Institute of Technology, Hyderabad, Telangana, India

Keywords: Natural Language Processing, Human‑Computer Interaction, Machine Learning, Conversational AI, User

Experience.

Abstract: This work addresses the revolutionizing power of Natural Language Processing (NLP) in improving Human-

Computer Interaction (HCI). Thanks to the rise of machine learning and deep learning, NLP has evolved into

an essential ingredient in building systems that appear to users as intuitive, adaptive, and user-focused. This

paper surveys recent trends, major challenges and exciting applications of NLP in HCI, specifically

considering new progress since the year of 2021 till 2025. By focusing on how NLP has been married to other

technologies including conversational AI, robotics, and gesture recognition, we emphasize the possibilities of

developing increasingly natural, personal, and convenient interfaces between humans and computers.

Moreover, the study highlights ethical implications and directions for future work on the NLP and HCI to

enable our interaction with intelligent systems in a natural and scalable manner.

1 INTRODUCTION

The rapid development of technology has had a big

impact on the monopolization of human-computer

interaction (hereafter, we will refer to FoOs as HCI),

meaning it becomes more nature, dynamic and

personalized. In the center of such revolution is

Natural Language Processing (NLP), a subfield in

artificial intelligence (AI) which deciphers and

enables computers to interpret, understand and

generate human language. With the growth of NLP,

the factorization of NLP and HCI systems is

important to improve user experience. NLP has

paved the way for new opportunities to build systems

that provide more natural and more intelligent

responses to the user inputs, by filling the critical

bridge between human communication and machine

understanding.

The convergence of NLP and HCI in recent years

has gained attention thanks to the development of

machine learning algorithms, conversational AI, and

multimodal interactions. These technologies are

transforming the way we approach our devices,

whether it be voice assistants or into machinery

itself, with robotics, VR and in healthcare for

example. But as these tech advances march ahead,

they also raise new issues, it's true, about scale and

ethics and access. In this paper, we map the state of

the art of NLP in HCI, with a focus on recent

advances and new applications in the period from

2021 to 2025. It is with this inquiry that we bring up

the prospect of (and need for) NLP to forge more

human-centered computing experiences that can

grow in step with users’ desires and expectations in

our increasingly digital world.

2 PROBLEM STATEMENT

Despite significant progress in NLP and HCI, a

number of remaining key challenges need to be

addressed in order to develop systems for real world

scenarios that are natural, adaptive, and intuitive

enough to understand and appropriately respond to

272

P., A. R., R., A., Jagatheeswaran, S., S., E. and Naik, S. K. L.

Advancing Human-Computer Interaction with Natural Language Processing: Emerging Trends and Applications.

DOI: 10.5220/0013862600004919

Paper published under CC license (CC BY-NC-ND 4.0)

In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies (ICRDICCT‘25 2025) - Volume 1, pages

272-278

ISBN: 978-989-758-777-1

natural human language. Although today's

technologies have significantly enhanced machine

understanding of speech and text, the technologies

often have difficulty understanding context,

emotional undertones, and nuances across cultures.

Moreover, the fusion of NLP and other modalities

such as gestures, facial expressions and brain-

computer interface is in the early stage; which

becomes one more challenge for achieving really

multimodal, personalized interactions. These

technological gaps are barriers to the realization of

genuinely intelligent systems that can deal with

highly dynamical, complex human behaviors across

diverse environments. Moreover, ethical implications

have increased even further since NLP is used to

process and analyze sensitive data such as image,

texts, sound among others, which has led to some

challenges in the mass use of NLP-based HCI system

such as privacy regarding personal data, accessibility

and lack of algorithmic transparency and biases. This

study aims to remedy these problems by examining

the state of the art in NLP in HCI, identifying trends,

and presenting viable solutions to the limitations that

continue to restrict the field.

3 LITERATURE SURVEY

The combination of NLP and HCI has attracted

increased attention recently, partly due to technical

advances in the two areas that make it possible to

design interactive systems that are capable of

understanding not only very simple, but also very

intuitive natural language input and be more

responsive. Applications Several studies have sought

to use NLP to assist the user interaction, including

voice assistants, chatbots, and multimodal

interaction. Pang et al. (2025) performed a systematic

literature review by investigating the incorporation

of LLM into HCI and focused on challenges and

opportunities the LLM would give. They noted

however, that although LLMs are powerful, their

integration into HHCI systems is still hindered with

relation to context comprehension and the

identification of user intent.

We could find the work of Heuer and Buschek

(2021) which examined the design and evaluation

techniques of HCI+NLP systems and suggested

frameworks that may help developers to build better

and more user-friendly systems. As a result, they

highlighted the necessity for evaluation metrics that

can effectively capture the quality of user interactions

for NLPbased HCI applications. Similarly, Zhang et

al. (2023) considered NLP techniques in the context

of interactive behavior modeling, towards predicting

and reacting to user behavior in real-time. Their work

highlights the promise of NLP for making user

interactions more context-specific, adaptive.

Inie and Derczynski (2021) have also investigated

the HCI–NLP divide and developed a framework IDR

(Interdisciplinary Research) to reveal the potential

and barriers among these two areas for future

research. Their study offers useful reflections about

how interdisciplinary work can promote more

integral solutions within HCI and NLP, while they

also mentioned major difficulties collecting the goals

of both fields. Xu et al. (2021) elaborated on these

thoughts, exploring the shift towards human

interaction with AI systems, and arguing that HCI

practitioners must conform to novel technology while

keeping systems focused on the user.

Rahman (2024) offered a substantive review of

the recent progress of NLP for HCI, highlighting that

deep learning methods have greatly changed the

manner in which systems interpret and are able to

process human language. Rahman’s findings added to

the evidence that NLP systems are getting better at

achieving complex tasks including sentiment analysis

and emotion recognition, and multi-turn

conversations. Similarly, Ali et al. (2024) focused on

the implications of NLP in HCI as it pertains to

improving user experience in different fields, such as

health care, customer service and entertainment.

Their effort demonstrates a potential for NLP to

support more customized, accessible interactions

across these domains.

User Experience and RoboticsApplications In the

section about NLP in HRI, a strond indication that

NLP can be used in Robotics that was found, is the

enhancement of user experience which is discussed in

the work of Kulkarni et al. (2023). They investigated

ambitious ways NLP might be able to help robots

respond to and interpret speech, improving human-

robot interactions. This agility promises exciting

potential in more natural and efficient robotic

systems, but there are still many challenges in real-

time processing and situational understanding that

must be addressed. Song (2024) summarised the

situation of NLP on these applications within HCI,

and described how NLP methods had been used to

improve the clarity and the naturalness of user

interfaces. He emphasized that despite the advances,

issues related to data quality, language ambiguity

and system performance need mitigation.

Bedi, (2024) highlighted their research on

conversational AI developments and their HCI

implications, noting that NLP has markedly increased

naturalness of human user’s interactions with AI

Advancing Human-Computer Interaction with Natural Language Processing: Emerging Trends and Applications

273

systems through voice and text. He emphasized the

promise of conversational agents in the context of

task completion, information acquisition and

personalized experiences and noted that a need to go

from current model’s incapacity to understand

nuanced user inputs. Joshi and Vibha (2023)

addressed hand gesture recognition in HCI with the

aid of NLP and suggested that when combined with

NLP, gesture recognition gives more creative

expression to the interaction. Though their findings

bring valuable information, they stated the difficulties

of embedding these techniques into real-time

systems.

Stilinki and Mohamed (2024) have studied the use

of NLP in robotics in the context of human-robot

interaction with the goal of providing the ability to

robots of understanding and interpreting human

orders in a most natural and intuitive form.

Nevertheless, they also acknowledged that the

integration of NLP with robotics is hindered by

several key problems, such as the contextual and

real-time processing constraints of robotic systems.

Abiagom and Ijomah (2024) discussed the influence

of AI-based language processing in customer service

with regards to response questions, yet the potential

of NLP could also improve the performance of

customer service systems and data with more engaged

and natural conversations. They also argued that as

NLP tech improves, so too will communications

between customers.

Lv et al. (2022) investigated the integration of

deep learning to intelligent HCI systems to

understand more complex and dynamic user input and

re stricted their focus on deep learning as the model

to understand user inputs. Their study demonstrates

the promise of using deep learning to increase the

accuracy of NLP systems in HCI, however they also

acknowledge the high computation cost of these

models. El Gedawy et al. (2025) proposed for the first

time the idea of EEG-to-text decoding, and exploited

deep learning to translate brain waves to text. This

new approach yields potential for non-invasive HCI,

exploiting the channel to provide communication for

handicapped persons however it struggles with

accuracy and noise reduction.

Blodgett et al. (2021) drew attention to

opportunities for the synergy of HCI and NLP, and

considered how these synergies may be used for more

user-centred systems. Although not without

challenges due to language ambiguity, privacy by

design, and fairness and inclusiveness factors to

enable systems that everyone can use), the authors

emphasized that NLP has the potential to

revolutionize HCI. The figure 1 shows the NLP-

Driven Research Workflow for Enhancing Human-

Computer Interaction. This extensive review paved

the way for further work on the integration of NLP

and HCI for the development of more intelligent and

adaptive user interfaces.

The literature review reflects the enormous

potential of NLP to transform HCI by supporting

more natural, personalized, and accessible systems.

But it also serves as a clear reminder of how much

work is left in developing contextual understanding,

how to deal with multimodal data, and what to do

when ethics get in the way. As further work in each

research area develops, the resolution of these issues

is likely to witness a progression towards more

advanced and user-adaptive interactive systems.

4 METHODOLOGY

This study is based on a wide-ranging investigation

of the role of Natural Language Processing (NLP) and

the development in the field of Human-Computer

Interaction (HCI). To scrutinize the diverse aspects of

this emerging field, a multistage approach is used

that integrates qualitative and quantitative techniques.

First, we conduct a comprehensive literature survey

of the recent literature in 2021-2025 to lay the

groundwork for understanding the state of the art,

challenges, and opportunities in the NLP-HCI

intersection. This review of the literature facilitates

the determination of substantive gaps in research and

provides the broad contours of the methodology.

Figure 1: NLP-driven research workflow for enhancing

human-computer interaction.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

274

Based on the literature review, empirical data is

collected by individual case studies and experiments

in this study to consider how NLP technologies are

being applied in various types of HCI systems. The

real-world studies cover a variety of use cases, such

as voice assistants, chatbots, robotic systems and

multimodal interfaces. The table 1 show the

Sentiment and Emotion Detection Accuracy in NLP-

HCI Systems. These cases serve as real-world

applications of how NLP is used for the improvement

of user interaction, and provide an insight into the

practical application of NLP across domains. In each

case study, comprehension of the user experience,

NLP capabilities in changing interaction features, and

the issues emerged during development are analysed.

Table 1: Sentiment and emotion detection accuracy in NLP-

HCI systems.

NLP Method

Sentiment

Detection

Accuracy (%)

Emotion

Recognition

Accuracy (%)

Deep Learning

(

LSTM-RNN

)

89.0 86.5

Transformer-

ased

(

BERT

)

94.2 91.8

CNN-based

NLP

86.3 84.0

Traditional ML

(SVM/Naive

)

78.0 75.5

Figure 2: Sentiment and emotion recognition accuracy in

NLP models.

User-centred experiments are carried out to

explore the benefits that NLP might provide for HCI.

These are typically experimenting in which different

NLP-based systems are evaluated under controlled

conditions and with real users. The subjects interact

with different HCI systems that provide the NLP

component whilst their responses, behaviors, and

evaluations are recorded. The figure 2 shows the

Sentiment and Emotion Recognition Accuracy in

NLP Models Information is gathered by means of

surveys, interviews and observations which provides

an overall picture of user satisfaction, ease of use, and

overall performance.

In addition, the study extends comparative NLP

techniques in HCI systems. The study tests these by

comparing their learning process in understanding

and processing human language to deep learning,

reinforcement learning, and traditional machine

learning approaches. This comparison can be used to

understand which methods are the most appropriate

for certain HCI applications with regards to accuracy,

scalability and user satisfaction.

The method also includes an ethical analysis of NLP

applications in HCI. Under the long-range effects in

threat to data privacy, bias in AI systems and

accessibility we paid a lot of attention to

understanding how to deal with these issues in the

analyzed literature. Ethical principles and

frameworks are examined, in order to universally

accomplish the proposed systems that promote

inclusion, transparency, and fairness.

Finally, a summary of the review of literature, the

discussion of case studies and experiments, as well as

the ethical reflection is offered to give a

comprehensive understanding of the status quo of

NLP in HCI. Results are employed to make some

suggestions toward overcoming the issues, as well as

recommendations for enhancing the system

performance and future research in the area. This

approach enables a holistic person-centred

understanding of how NLP technology can replace

human-human and humancomputer interactions in

increasingly complex, evolving tasks.

5 RESULTS AND DISCUSSION

The findings of this study suggest that NLP has

significantly changed the HCI landscape for more

intuitive, adaptive, personalized user experiences.

Based on the case studies and empirical experiments

that we carried out, we find that NLP integrated

system is more responsive to the user's input, and

provides a naturalistic and smoother interaction with

the user. For instance, in voice assistant, users could

interact with systems with a more conversational,

natural language and achieve better satisfaction and

engagement. Likewise, in robotics, adding NLP

resulted in a more natural interaction, where users

could instruct robots in colloquial language, with a

lesser focus on standardised, well-defined

commands.

Yet even as the progress is exciting, there are still

many hurdles to be overcome. The table 3 shows the

Advancing Human-Computer Interaction with Natural Language Processing: Emerging Trends and Applications

275

Performance Metrics for NLP-based Robotic Systems

Interaction

A principal problem encountered in the

experiments is the effective utilization of context and

the interpretation of ambiguity in the user input. The

figure 3 shows the Accuracy Comparison of NLP

Techniques in Voice Interaction Systems. The table

2 shows the Accuracy Comparison of NLP

Techniques in Voice Interaction Systems. NLP

solutions, as powerful as they were, sometimes had a

hard time understanding complex or nuanced

language, with a few misunderstandings or non-

responses as result. This was particularly true in

multi-turn dialogues; there was memory, and limited

context, and a need for inference. Furthermore,

multimodal inputs (e.g., gestures, facial expressions)

were difficult to incorporate. These types of data

were not all the time easy to handle and synchronize

by systems which affected their performance and

usability.

Table 2: Accuracy comparison of NLP techniques in voice

interaction systems.

NLP

Technique

Accur

acy

(%)

Average

Response

Time (ms)

User

Satisfactio

n Level

Transform

er-based

Models

92.5 350 High

Recurrent

Neural

Networks

87.0 400 Moderate

Convoluti

onal

Neural

Networks

85.5 300 Moderate

to High

Reinforce

ment

Learning

89.0 450 High

Traditiona

l ML

Algorithm

78.5 250 Moderate

Figure 3: Accuracy comparison of NLP techniques in voice

interaction systems.

Table 3: Performance metrics for NLP-based robotic

systems interaction.

Robotic

Task

NLP Model

Used

Command

Recognition

Accuracy (%)

Task

Completion

Rate (%)

Simple

Comman

Executio

Transforme

r-based

NLP

94.5 92.0

Conversa

tional

Dialogue

Reinforcem

ent

Learning

NLP

90.0 88.5

Gesture-

based

Comman

Multimodal

NLP

Integration

88.0 85.0

Complex

Task

Executio

Hybrid

NLP

(Transform

ers +

LLMs)

91.5 89.5

Figure 4: Response time of NLP techniques in robotic

systems.

In its comparative study of different NLP

techniques, the TaskForce realized that although deep

learning such as transformer models demonstrated

accurate language comprehension, they were

computationally expensive and demanded

considerable resources to be effective. Conventional

machine learning models, while computationally less

costly, are unable to achieve the accuracy and deep

understanding afforded by newer and more elaborate

models. The figure 4 shows the Response Time of

NLP Techniques in Robotic Systems This

performance-resource mismatch is a challenge that

persists in the balance between efficiency and

accuracy for NLP-based HCI systems.

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

276

Table 4: EEG-To-Text NLP decoding accuracy for

accessibility applications.

Decodin

Techniq

Word

Recogniti

Accuracy

(%)

Sentenc

e-level

Accurac

y (%)

Noise

Filtering

Efficiency

(%)

Deep

Learnin

g-based

NLP

85.0 78.5 90.2

Transfor

mer-

based

Models

88.5 82.3 92.8

Recurre

Neural

Networ

81.2 75.0 86.5

Figure 5: EEG-to-Text decoding accuracy over increasing

noise levels.

Ethical issues also stood out as a key feature of

the research. Privacy, algorithmic bias and

accessibility were found to be major barriers to the

application of NLP in HCI. Although safeguards were

built into some systems to guard against exposing

sensitive user information, much remained opaque

about how data was gathered and processed, the

researchers found. The figure 5 shows EEG-to-Text

Decoding Accuracy over Increasing Noise Levels

Bias in AI algorithms also continued to be an issue,

especially in voice recognition systems that were

often unable to correctly understand what was being

said by people with accents or speaking non-standard

dialects. Solving these challenges is of great

importance for guaranteeing that NLP-based HCI

systems are just and inclusive for all users.

The results further pointed to additional

opportunities for integration of NLP in broader

applications that range from healthcare to education.

In the healthcare space, for example, NLP-powered

chatbots and virtual assistants showed their potential

to disseminate timely health information as well as

advice, thereby making healthcare more reachable.

The table 4 shows the EEG-to-Text NLP Decoding

Accuracy for Accessibility Applications In education,

NLP-based techniques have been used to enrich

learning experiences with interactive personalization

capabilities of tutoring systems. But both of these

sectors had issues around accuracy of information and

ethical use of information.

Finally, the application of NLP in HCI could play

a revolutional role in improving human interactions

with systems. Mir 1 forms a strong foundation for the

project overall, though a number of challenges

context understanding, multimodal integration,

computationally efficient and ethic considerations

still need to be further studied and tackled. Further

development of more sophisticated algorithms that

are capable of processing complex language inputs

in an efficient and accurate fashion is needed. Fur-

ther, topics of ethics – a term often bandied about, but

difficult to pin down – will also need to be dealt with

transparently, through justice and due consideration

of all parties, to carry NLP for HCI to its next phase

of sustained applicability. This work provides a

starting point for future studies in this area with the

goal of developing more intelligent, user-friendly and

ethically responsible systems.

6 CONCLUSIONS

To sum up, combining NLP with HCI has opened up

new doors to develop much more intuitive, adaptive

and user-friendly systems. The work carried out

under this project has demonstrated that NLP can

advance the state-of-the-art in the extent to which

systems understand and respond to human language,

thus facilitating a more natural user interaction, and

engagement. Advances on deep learning, machine

learning, and multimodal interfaces enable more

intelligent and user-friendly system performance as

communication between human and machine

becomes transparent. Nevertheless, problems like

resolving language ambiguity, considering context in

multi-turn dialogue and integrating different input

modalities in a smooth way are still common.

And the ethics aspects, especially in terms of data

privacy, algorithm bias and accessibility, are

highlights that we should continue to pay attention, to

make NLP-based systems more inclusive,

transparent and fair. As our findings demonstrate,

NLP has great potential to transform HCI but also

must be approached thoughtfully and responsibly in

order to not compound existing disparities or create

new barriers. Our future work in this area is to

address these challenges by researching more

efficient and effective NLP algorithms, enhancing the

Advancing Human-Computer Interaction with Natural Language Processing: Emerging Trends and Applications

277

interactive capabilities of massive modalities and

dealing with the ethical and social issues of these

technologies. After all, the long term mission should

be to build systems that improve user experience,

while respecting user agency, inclusiveness and

fairness. This work sets the stage for continued

exploration and discovery at the intersection of NLP

and HCI, guiding the field to more intelligent,

ethical, and user-centered technologies.

REFERENCES

Abiagom, C. N., & Ijomah, T. I. (2024). Enhancing

Customer Experience through AI-Driven Language

Processing in Service Interactions. ResearchGate.

https://www.researchgate.net/publication/386139323_

A_Review_of_The_Application_of_Natural_Languag

e_Processing_in_Human-Computer_Interaction

Ali, W., Siraj, S., Lakho, S., & Ali, A. (2024). Investigating

the Applications of Natural Language Processing in

Human-Computer Interaction. Policy Research

Journal, 2(4), 598– 608. https://policyresearchjournal.c

om/index.php/1/article/view/107

Arifin, Y., & Soeharyadi, M. C. (2024). Machine Learning

Algorithms in Natural Language Processing for

Improved Human-Computer Interaction. International

Journal of Communication and Information

Technology, 5(1), 26– 28. https://www.computerscien

cejournals.com/ijcit/archives/2024.v5.i1.A.75

Bedi, A. (2024). Advancements in Conversational AI:

Enhancing Human-Computer Interaction with Natural

Language Processing. Shodh Sagar Journal of Artificial

Intelligence and Machine Learning, 1(3), 6–9.

https://doi.org/10.36676/ssjaiml.v1.i3.17

Blodgett, S. L., Madaio, M., O’Connor, B., Wallach, H., &

Yang, Q. (2021). Bridging Human–Computer

Interaction and Natural Language Processing.

Microsoft Research. https://www.microsoft.com/en-

us/research/publication/bridging-human-computer-

interaction-and-natural-language-processing/

El Gedawy, M., Nabil, O., Mamdouh, O., Nady, M., Adel,

N. A., & Fares, A. (2025). Bridging Brain Signals and

Language: A Deep Learning Approach to EEG-to-Text

Decoding. arXiv. https://arxiv.org/abs/2502.17465

Heuer, H., & Buschek, D. (2021). Methods for the Design

and Evaluation of HCI+NLP Systems. Proceedings of

the First Workshop on Bridging Human–Computer

Interaction and Natural Language Processing, 28–33.

https://aclanthology.org/2021.hcinlp-1.5/

Inie, N., & Derczynski, L. (2021). An IDR Framework of

Opportunities and Barriers between HCI and NLP.

Proceedings of the First Workshop on Bridging

Human–Computer Interaction and Natural Language

Processing, 101– 108. https://aclanthology.org/2021.h

cinlp-1.16/ACL Anthology

Joshi, R., & Vibha, M. B. (2023). Hand Gesture Detection

for Human-Computer Interaction: A Natural Language

Processing Approach. International Journal of

Engineering Research & Technology (IJERT), 11(06).

https://www.ijert.org/hand-gesture-detection-for-

human-computer-interaction-a-natural-language-

processing-approach

Kulkarni, R., Varade, P., & Yellalwar, R. G. (2023). NLP

and Human-Computer Interaction: Enhancing User

Experience through Language Technology.

International Journal for Research in Applied Science

and Engineering Technology (IJRASET).

https://www.ijraset.com/research-paper/nlp-and-

human-computer-interaction-enhancing-user-

experience-through-language-technology

Lv, Z., Poiesi, F., Dong, Q., & Song, H. H. (2022). Deep

Learning for Intelligent Human–Computer Interaction.

ResearchGate. https://www.researchgate.net/publicati

on/384643026_Natural_Language_Processing_NLP_

Techniques_Usability_in_Human-

Computer_Interactions

Pang, R. Y., Schroeder, H., Smith, K. S., Barocas, S., Xiao,

Z., Tseng, E., & Bragg, D. (2025). Understanding the

LLM-ification of CHI: Unpacking the Impact of LLMs

at CHI through a Systematic Literature Review. arXiv.

https://arxiv.org/abs/2501.12557

Rahman, M. M. (2024). Advancements in Natural

Language Processing for Human-Computer

Interaction. Global Mainstream Journal of Innovation,

Engineering & Emerging Technology, 3(05), 1–10.

https://doi.org/10.62304/jieet.v3i05.216

Song, J. (2024). A Review of The Application of Natural

Language Processing in Human-Computer Interaction.

Applied and Computational Engineering, 106(1), 111–

117. https://www.researchgate.net/publication/386139

323_A_Review_of_The_Application_of_Natural_Lan

guage_Processing_in_Human-Computer_Interaction

Stilinki, D., & Mohamed, S. (2024). Bridging the Gap

Between Natural Language Processing (NLP) and

Robotics for Human-Robot Interaction. EasyChair

Preprint 13894. https://easychair.org/publications/pre

print/nG2f

Xu, W., Dainoff, M. J., Ge, L., & Gao, Z. (2021).

Transitioning to Human Interaction with AI Systems:

New Challenges and Opportunities for HCI

Professionals to Enable Human-Centered AI. arXiv.

https://arxiv.org/abs/2105.05424arXiv

Zhang, G., Bortoletto, M., Hu, Z., Shi, L., Bâce, M., &

Bulling, A. (2023). Exploring Natural Language

Processing Methods for Interactive Behaviour

Modelling. arXiv. https://arxiv.org/abs/2303.16039

ICRDICCT‘25 2025 - INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION,

COMMUNICATION, AND COMPUTING TECHNOLOGIES

278