Questions related to Chatbot
I am new to chatbot development and NLP. I wanted to know if it is possible to use extractive text summarization algorithms in the rasa chatbot development framework.
Thank you in advance
I have been trying to find good research papers about how chatbot integration might assist businesses to improve their customer engagement. Can you guys suggest me to some research papers and jornals?
Would a chatbot be a supportive tool to LMS instructors? If Yes
Can supporting instructors have an impact on LMS usage?
What barriers can be expected when dealing with a chatbot as a supportive tool?
I pray you are well.
Am humbly looking out for expert panelists that can review my research instruments in relation to a study on customer experience in relation to usage of chatbots. My defense in due soon, so appreciate an urgent response. Please reach-out so that I may share the instruments. They are composed of a questionnaire, interview guide and focus group discussion guide. Details; HOW DOES THE USE OF A CHATBOT IN SAFARICOM PLC INFLUENCE CUSTOMER EXPERIENCE? Doctoral Study Project (DSP) Presented to the Glenn R. Jones College of Business of Trident University International in Partial Fulfillment of the Requirements for the Degree of Doctor of Business Administration
I've got a question regarding within-subject experiments, in which two or more variants of a prototype (e.g., chatbot) are evaluated with respect to different constructs, I.e. classic A/B testing experiments of different design options. For both versions, the same items are used for comparability.
Before the final data analysis, I plan to perform tests for validity, reliability and factor analysis. Does anyone know if I need to calculate the corresponding criteria (e.g., Cronbach's alpha, factor loadings, KMO values) for both versions separately, or only once aggregated for the respective constructs? And how would I proceed with the exclusion of items? Especially when there are a lot of control conditions, it might be difficult to decide whether to exclude an item if it is below a certain criterion.
In reviewing the literature of papers with a similar experiment design, I couldn't identify a consistent approach so far.
Thank you very much for your help! If anyone has any recommendations for tools or tutorials, I would also appreciate it as well.
Lets say I use a literature review, a survey (qualitative) and a case study in which, for example, the development of a chatbot is carried out to answer which factors influence the development of a chatbot (topic). Do I have to use Design Science Research Paradigm (DSR) for this or not? So is or could DSR be applicable to my case? And if so, do I have to follow the certain steps of this approach or can I make adjustments?
im currently writing my master thesis and using extended UTAUT model to analyze the adoption of chatbots.
what kind of statistical method would be the most appropriate here to analyze the influence of independent variables (for example perceived usefulness, enjoyment , trust, etc) on intention to adopt a technology. the survey is 5 likert scale. Around 33 questions in total. Each variable has 2 to 3 measures (Questions)
thank you in advance for your help
I have been reading certain publication that mainly talks about Artificial Intelligence and how it affects behavioural capability in general (DOIs:10.1007/s10676-021-09598-8, 10.1177/2057047320950636, 10.2196/22845, 10.1007/s41649-018-0061-0, and so on). Along with the exponential progression of AIs in certain applications (Such as, but not limited to, Chatbots programmes).
It seemed somehow apparent to me, that there have been emotionalization towards AIs, such as employing it as friend. Of course the depicted AIs in popular culture references and sci-fis are, well of course still currently in the realm of "Sci-fi".
But seeing the progression, along with the prolonged isolation from social interaction (mainly due to pandemic) in many countries. How should we view such term? Especially towards the notion of self-consciousness, humanization, and of course biological realization in human-bots interaction?
Is it something that we must stay neutral, look forward upon, or perhaps an inevitable shift that will forever change how we view the norm.
I am trying to develop architecture for Customer-Agent smart reply system for chat bot. I am taking help of Googles paper published in 2016:
This talks about smart reply in Gmail use case scenario. And our objective is to do it for chat-bot case scenario where Agent and Customer Utterances happen.
The problem that I am facing is:
How should I structure my Input/ Feed my input (i.e, Agent-Customer Utterances) for the downstream model to get the top 3 or 5 responses? How model should understand that which is Agent and which is Customer Utterances?
Input looks like:
Agent: Welcome to XYZ. How can I assist you?
Customer: I am facing issue withe internet?
Agent: May I know your registered mobile number?
Customer: My mobile number is XXXX. My email ID is XXX@yyy.com.
Customer: Please resolve my issue asap.
Customer or Agent can have more than one utterances and one Utterances can have more than 1 sentences in that session.
How the input should be fed to model so that we get desired smart reply?
Like in the above example it can be:
Agent Smart Reply 1: We are working on it Mr.XXX
Agent Smart Reply 2: Your issue is resolved. Thanks for contacting XYZ
Agent Smart Reply 3: Your issue will take some time to get resolved. Please wait for 24 -48 hrs.
How we can fed the Customer-Agent Utterances to model? Any paper with reproducible code or any new suggestion will be helpful.
I am planning to develop a chatbot .If anyone have Knowledge about chatbot, please contact me at 'email@example.com ' . Please I really need your help. If anyone knows about chatbot , please help me with it. I will be really grateful , if anyone interested , please contact me at given email ID. Thank you.
can someone point me to a university, which currently does research on the application of AI in higher education (preferably AI chatbots)? I am going to start s research this fall as a Ph.D. candidate, and it would be great to have some advisor or just to know another scholar with the same aim, especially in case I would have the opportunity to become a visiting student with my university exchange program. Thank you!
With our current speech-to-text/text-to-speech technology and conversational agents like Siri and Alexa seemingly everywhere, why aren't we creating powerful new tools to support language learning? What is holding us back? What do we need in order to push forward?
I am building an Intelligent Career Counseling chatbot. Which will provide guidance to college graduates in choosing their career path based on their background, Interest Inventories, values Inventories, and aptitude assessment.
Will be happy to work with a volunteer.
The chatbot has been implemented using deep learning techniques. can anyone please suggest an efficient and effective way to measure the performance so that it can be compared with other implementations that has been done in the past. In some researches i saw that many researchers used Bleu and perplexity for the same and some researchers just gave the accuracy in term of percentage.
Please let me know if you have any question so that we can make this discussion fruitful.
I'm curious to hear about challenges teachers face when integrating chatbots into their lessons. I feel communication breakdown is one of the biggest problems with chatbots in education for obvious reasons. What other issues might arise when introducing chatbot activities into class?
I am currently working on a open domain chatbot implementation using Deep Learning (RNN to be specific) . While training the seq2seq model, I am facing one of the biggest challenge which is amount of time required to train the model. I am using a system with average configuration 8gb ram with i5 processor to be precise.
Can you please suggest a way to boost up the process. It will be a great help.
Nowadays, artificial intelligence (AI) played a big role in improving most of our daily activities. in E-commerce, Chatbots, voice search, augmented reality, and other AI methods and tools can help users to have a better shopping experience. In your opinion, what are other AI tools and methods that can be developed to enhance E-commerce?
I am in the process of developing the article titled "HUuan Resources Development through Chatbots using Artificial Intelligence – A study" - Kindly suggest the methodology part. What kind of analysis will opt for such studies?
I am trying to develop a simple chat-bot to receive instruction from a user and generate a SQL query from it. Since I am new to NLP and NLU, I thought I will start from scratch with syntax and semantic analyzer. From the lessons I had in compiler design course, I could come up with a grammar for my text input and even a semantic rules to generate the SQL instruction. I thought I will go with Python for actual implementation and I came to know about NLTK libraries to implement a parser to parse my input. It works. However, when dealing with terminals I had to generate a lot of productions and corresponding semantic rules. Is there a better way to handle this problem that I should look into? Please provide me some idea on how to go about it.
Any help is appreciated. Thanks.
VOC is certainly nothing new. The more brands understand their customers, the better they are able to create products and services that meet their needs, gain competitive intelligence, and identify shifts in purchasing intent and behavior.
Artificial intelligence and automation are increasingly unlocking new and exciting types of VOC data that is more actionable for decision makers. Through the adoption of AI and machine learning, companies can gather data from all their customers, not just a small sampling that has interacted with their brand through a survey. AI enables a much deeper understanding of customer behavior and satisfaction, including voice, facial analysis, and chatbot technology. AI technology for VOC insights will continue to grow in 2020, along with the software companies who are bringing to market new and better methods to measure and analyze data and predict consumer behavior.
Have a read on to my new publication:
I am doing a research project on the acceptance of a chatbot (AI) technology for business coaching. The purpose of my research is not to design the instrument, but it is important that I use a validated instrument to ensure validity. Thank you for your support in advance.
I'm currently writing my master thesis in media studies about news presentation through sequential chatbots (not AI-based).
I've made a Messenger chatbot which will present a specific news case I've adapted from a regular newsstory and pre-written everything. The newsstory is presented through a dialogue tree-style, so the user is interactive and have to decide what they want to know more about in the specific news case. The bot will be tested by ten informants who will be interviewed after the user test about usability and understanding of the news case.
So far I've written about various hypertext theories and usabilitiy theories, but I feel something is lacking. Any ideas on what I might add in addition? Since this is a practical-theorical thesis, and I've mainly done other types of assignments in the past, I'm not too familiar with human-computer interaction (HCI) and things like that - is this even relevant from a media science perspective?
Thanks in advance
Making anxiety controlling/monitoring AI Chatbot based mobile application. Looking for the best way to create the bot.
Best way to make a bot to be integrated into Android application?
The only datasets available are under LDC licenses, and I'm not sure if the authors are allowed to provide me the datasets for free if I asked them.
Also, any idea on where to scrap for Arabic chat datasets?
Many restaurants deploy automation, artificial intelligence and machine learning, using innovations such as chatbots to guide customers through menus and help them place order. Some restaurants make use of robots to perform tasks such as delivering food and drinks to the table. Do you prefer traditional or automated/robotic restaurant?
Natural Language Inference(NLI) is the task of predicting the labels(entailment, contradiction, and neutral,) for sentence pairs.
People invent a lot of deep model to solve this problem.
But I can not think of some application or scenario for this kind of deep model.
I have the following statistical problem with my Masterthesis: I have collected quantitative data, it is about the satisfaction with a chatbot. I asked the satisfaction (scale 1-7) about 33 different criteria (e.g. grammatical correctness, professionalism,...) as well as the overall satisfaction with the chatbot (also scale 1-7).
I already checked the data for multicollinearity. Due to that I delted two variables for further analysis. So I have 31 variables left. I expect them to have a positive influence on the dependet varaible.
I would now like to carry out a multiple regression in which I check which criterion has the greatest influence on overall satisfaction. The result of the regression is quite strange. Only 3 of the 33 variables are significant. Of these 3 variables, however, 2 have a negative regression coefficient, which in terms of content would mean that if satisfaction with these criteria were higher, overall satisfaction would decrease. This makes no sense in terms of content alone.
I have now carried out a simple regression of all independent variables to the dependent variable. The result is that all variables have a significant and positive influence on overall satisfaction.
Can anyone tell me what the exact statistical explanation for this is and whether there is an argument in the literature that says that in certain situations (e.g. inadequate validity or reliability) instead of multiple regression one may resort to a simple regression?
And could there are be a suppression effect? How exactly do I find it out?
Many thanks in advance!
Dear Mr. Brandel,
Regarding your experience in Chatbot concept, is there any highly agreed work on, let me say emotional or companion chatbots, please?
Could anybody tell me something about already ready-made filler chatbots that I can use between a user utterance and robot response to fill the moment of silence?
With kind regards,
My research topic is "examining the impact of chatbot persona on customer engagement" . So, for that I need to know (with backing of acamedic journals),whether personality does really affect the engagement.
I am currently writing my masters thesis on the future of the Insurances Industry and more specifically hoe AI might change the way of how business will be done.
Think about long administrative procedures being replaced by Chatbots, automatic claim paybacks, ...
How do you think Artificial Intelligence will change the business? Do you think there are other technologies as well that might influence the Industry by 2030?
I'm looking forward to your responses!
The aim is to make a web service available that conducts an oral open-text test on factual knowledge and to research on its impact on the learning outcome (with students in higher education).
In a first step, I'm looking for the currently most advanced services to automatically generate different types of questions from a written text passage / textbook. The questions are to be generated automatically (...and later the students answers are to be evaluated automatically).
Who knows more about that?
I consider a mixed method project inquiring into the affective states of AI chatbot users in an attempt to discuss the issues of differentiation and acceptability in the HRI dyad in context of a Customer Service situation.
I am looking for experts to provide insights into "Which characteristics of Social Intelligence should future bots be able to master?". Who's interested? Any suggestions who could fit? #HCI #SIA #AI #NLP #Robotics #SocialIntelligence #Chatbots #MachineLearning #CognitiveScience
Suppose I have a lot of data on conversations between humans and chatbots (human text, chatbot text, times, media used for chat, etc), and I want to be able to detect anomalies in these conversations. For example, an anomaly would be if the chatbot was supposed to help customers with navigating a website, but the website was down and displayed some sort of error. As a result, the chatbot gets a lot questions about that error in a "short window" of time. I want to be able to detect this quickly, so I can then make the chatbot be able to better handle questions about that error. I read "Incremental Tensor Analysis: Theory and Applications" by Sun, Tao, et al. but I was curious if there were other works that were more applicable to text and conversations that I should check out.
iam research scholar,doing research on same work as creating question answering system for closed domain fon natural language as interactive chatbot for students for specific course.
example: what is DBMS?
i should get precise answer as data base management system..
i have lot of doubts regarding design of dataset ,which classifier can be used and whether preprocessing is required for question,which matching technique to used for my application..please suggest and help me for my work..
To achieve sentiment Analysis using NLP, there is more than one way to get results. Which according to you is a suitable implementation? Bag of Words or Word2Vec. Kindly Provide some resources for the same.