Navigating the Generative AI Landscape

The emergence of generative artificial intelligence (AI) presents exciting possibilities for teaching and learning. These large language models generate text, translate languages, write different kinds of creative content, and even answer users' questions. But with several options, deciding which generative AI to explore is daunting. In this article, we briefly explore ChatGPT, Bard, and Claude to help you navigate the generative AI landscape.

ChatGPT (Open AI) excels at generating creative text formats, like poems, code, scripts, musical pieces, and even emails. As a creative text generator, its strength lies in its conversational fluency, engaging users in open-ended dialogues, and producing creative text formats. Its ability to adapt to different writing styles and tones makes ChatGPT a valuable tool for brainstorming ideas, exploring different perspectives, and practicing writing skills. However, ChatGPT's focus on creativity can sometimes come at the expense of factual accuracy. Its outputs may lack citations or references, and its understanding of complex topics is sometimes limited. However, concerns regarding potential bias and misinformation in ChatGPT necessitate careful monitoring and face-checking of its responses (Sætra, 2023).

On the other hand, Bard (Google AI) prioritizes factual accuracy and information retrieval. Bard leverages Google’s vast knowledge base to provide informative and comprehensive answers. Bard is great at summarizing articles and papers or generating reports. It provides citations and references to support its claims, making it reliable for research and academic writing. However, Bard's focus on factual accuracy sometimes makes its responses seem less creative or engaging than ChatGPT. Bard’s ability to generate creative text formats is still under development (Tan, Chen, & Chua, 2023).

Claude strikes a balance between ChatGPT’s creativity and Bard’s factual accuracy but prioritizes ethical interactions and responsible AI development (Anthropic, 2023). Claude excels at identifying and mitigating potential biases in its responses, making it suitable for tasks requiring sensitive information or ethical considerations and promoting inclusive learning environments. However, Claude is still under development and may not be as refined as ChatGPT or Bard in some areas. (Gabriel, 2020).

In summary, ChatGPT, Bard, and Claude are key players in the generative AI landscape. They possess unique features and potential applications. For generating writing prompts, creating outlines, crafting distinct character voices, or assisting with brainstorming ideas, ChatGPT acts as a writing partner. Bard and Claude are options for fostering historical understanding and encouraging critical thinking. Bard’s online access facilitates accurate information on historical events and figures. Claude, with its emphasis on safety and minimizing bias, provides fair and objective debate opportunities. Bard and ChatGPT hold potential as personalized learning assistants with Bard's responses being more factual while ChatGPT's engaging conversational style makes learning more interactive. For assisting with coding practice, both Bard and Claude demonstrate promise. Bard’s access to technical information is invaluable in explaining complex concepts or identifying errors in student code. Claude’s commitment to safety fosters a secure learning environment. As these models continue to learn and improve their potential to assist users will continue to grow.

References

Gabriel, I. (2020). Artificial intelligence, values, and alignment. Minds & Machines 30(3), 411–437. https://doi.org/10.1007/s11023-020-09539-2

Sætra, H. S. (2023). Generative AI: Here to stay, but for good? Technology in Society, 75, 102372. https://doi.org/10.1016/j.techsoc.2023.102372

Tan, S. C., Chen, W., & Chua, B. L. (2023). Leveraging generative artificial intelligence based on large language models for collaborative learning. Learning: Research & Practice, 9(2), 125–134. https://doi.org/10.1080/23735082.2023.2258895

__________________________________________________________________________

Washington, G. (2024, January 31). Navigating the Generative AI Landscape [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Photo by Mohamed Nohassi on Unsplash

Claude 2: An Alternative to ChatGPT

 

We have witnessed an explosion in the development of large language models (LLMs). These AI-powered systems, trained on massive datasets of text and code, can now generate human-quality text, translate languages, write various kinds of content, and even answer your questions in an informative way. OpenAI's ChatGPT opened doors in conversational artificial intelligence (AI), but Anthropic's Claude 2 steps onto the stage with a transformative vision. Claude 2 offers distinct features and capabilities that make it a compelling alternative, particularly for educational settings.

What is Claude 2?

Claude 2 is an updated version of Claude, an AI assistant created by startup Anthropic, an AI safety and research company. It employs natural language processing to answer questions, have discussions, and generally assist users through written conversations (Anthropic, 2023). Relative to the original Claude model, Claude 2 demonstrates enhanced conversational abilities, more comprehensive knowledge of a diversity of topics, and improved common sense comprehension for contextual responses.

A distinctive feature of the Claude 2 model involves its adherence to Constitutional AI principles, meaning its design intentionally constrains certain possibilities in favor of increased safety (Gabriel, 2020). Claude 2 is trained to be helpful, harmless, and honest while focusing on avoiding toxic, biased, or misleading responses. Its training incorporates reinforcement learning from human feedback. Claude 2 prioritizes truthfulness, cites its knowledge sources, and acknowledges the boundaries of its understanding. It is designed to be safer than competing models, such as ChatGPT and Bard (Anthropic, 2023).

In addition, Claude 2 has an expansive 100,000-token context window which allows it to analyze prompts deeply and respond with precise, well-referenced answers. Claude 2 thrives in extended dialogues and complex tasks with consistently relevant and informed responses (Anthropic, 2023). Its unique features unlock opportunities for personalized learning and inquiry-based exploration within educational settings.

Benefits of Claude 2 for Education

Claude 2 can adapt explanations and examples to individual learning styles making it a powerful tool for personalized, engaging, and empowering learning experiences. Its adaptive nature allows it to adjust explanations and examples, therefore, fostering personalized learning experiences. It can generate learning materials, help find relevant sources, and even identify factual inconsistencies, turning students into active participants in their learning journey.

Also, Claude 2 excels in open-ended dialogue and inquiry-based learning. Its conversational ability promotes active participation, critical thinking, and deep understanding of complex topics. It assists in content creation, research, and problem-solving, equipping students with the tools to become independent learners and explore their interests.

How to try Claude 2

You can access Claude 2 through a new public-facing website, Claude.ai, which is currently in open beta. From there, you talk to Claude by starting a conversation or using one of Claude's default prompts. Anthropic recently introduced Claude Pro, a paid plan for their Claude.ai. You can also access Claude through Quora's Poe, which allows you to interact directly with the Claude 2 100K model (among other AI models).

Conclusion

Claude 2's advanced capabilities present a promising alternative to ChatGPT. As a safety-focused conversational language model, Claude 2’s use in educational settings provides a valuable tool for fostering deeper learning, critical thinking, and personalized learning experiences. Its potential for transforming educational practices should be further explored and evaluated through rigorous research.

References

Anthropic. (2023). Claude 2: AI assistant focused on safety. https://www.anthropic.com

Gabriel, I. (2020). Artificial intelligence, values, and alignment. Minds & Machines 30(3), 411–437. https://doi.org/10.1007/s11023-020-09539-2

__________________________________________________________________________

Washington, G. (2023, December 31). Claude 2: An Alternative to ChatGPT [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Bard – Google’s Conversational AI

The release of ChatGPT free version GPT 3.5 by OpenAI sparked the appearance of other generative large language models (LLMs), such as Google Bard. LLMs are a type of artificial intelligence (AI) trained on a massive dataset of text and code. They learn the statistical relationship between words and phrases to generate responses that are like human-written text. Like ChatGPT, Bard responds to prompts or questions. Bard generates text, translates languages, writes different kinds of creative content, and answers questions in an informative way. As an AI chatbot, Bard is meant to be a rival to the popular ChatGPT. This article introduces Bard, discusses how it can be used in education, and compares it to ChatGPT.

What is Bard?

In February 2023, Google revealed its conversational AI called Bard in response to ChatGPT. Bard was based on Google's Language Model for Dialogue Applications (LaMDA). It uses machine learning and natural processing techniques to generate human-like text responses to various prompts. Bard draws on information from the web to provide direct responses to prompts and questions (Pichai, 2023). When you ask Bard a question or give it a prompt, the model uses its knowledge of the world to generate an answer. The model also uses its knowledge of language to make sure that the answer is grammatically correct and easy to understand. It represents a significant advancement in AI technology creating entirely new ways to engage with information.

How to Use Bard?

Bard was originally available to a limited number of users. It is still labeled as an “experiment,” but it is now available to everyone. To access Bard, go to bard.google.com in a browser and sign in with a Google account. Enter a prompt or question, either by typing or selecting the microphone and talking. Press enter or return and wait for Bard’s response. Once Bard responds with an answer, you receive a set of optional actions: View other drafts to access drafts of the same answer, Regenerate drafts to have Bard attempt another answer, Edit the prompt by clicking the pencil icon, Google It to switch to a standard keyword search query derived from your prompt, Share & Export the response, Copy the content to paste into another application, Report a legal issue to signal a significant content concern, provide feedback with a thumbs up (Good Response) or down (Bad Response) or enter another prompt to continue the chat.

Here are some ways to use Bard (Bard, 2023).

• Answer questions: Bard can be used to answer questions about any topic. It can provide summaries of factual topics or create stories.
• Generate text: Bard can be used to generate text, such as poems, code, scripts, musical pieces, emails, letters, etc.
• Translate languages: Bard can be used to translate languages.
• Write different kinds of creative content: Bard can be used to write different kinds of creative content, such as poems, stories, or scripts.
• Collaborate with others: Bard can be used to collaborate with others on projects.
• Access and process information from the real world: Bard can access and process information from the real world through Google Search and keep its response consistent with search results.

In education, AI can deepen our understanding of information and turn it into useful knowledge.

Bard in Education

Bard has the potential to have a significant impact on education. It could be used to personalize learning, promote active learning, facilitate collaborative learning, and provide access to information. Personalized learning involves identifying the student's strengths and weaknesses, and then creating a plan that focuses on the areas where the student needs the most help. Active learning in the classroom promotes engagement by posing questions to students, encouraging them to think critically and creatively, and helping them to learn by doing. Collaborative learning helps students to work together on projects, share ideas, and learn from each other. Bard provides students with access to a vast amount of information. This could help them to find information on any topic and to learn about different perspectives. Bard has the potential to motivate students to learn.

Bard vs ChatGPT

Both Bard and ChatGPT are large language models trained on massive datasets of text and code. They are both capable of generating human-quality text, translating languages, writing different kinds of creative content, and answering questions in an informative way. Both are still under development, which means they are constantly being improved and are likely to become even more powerful and versatile in the future. Both have the potential to be used on a wide range of tasks. However, there are some differences between the chatbots.

One of the biggest differences between Bard and ChatGPT is the data they are trained on. Bard is trained on a massive dataset of text and code, including scientific papers, mathematical expressions, and source code. This gives Bard a strong foundation in technical topics and allows it to generate more accurate and informative responses. ChatGPT, on the other hand, is trained on a dataset of text from the internet. This gives ChatGPT a wider range of knowledge, but it also means that it is more likely to generate inaccurate or misleading information (Bard, 2023).

Another difference between Bard and ChatGPT is their access to information. Bard has access to the internet, which means that it can always get the latest information. ChatGPT, on the other hand, is limited to the information that was included in its training dataset. This difference in access to information can be seen in the way that Bard and ChatGPT answer questions. When asked a question, Bard will often go out and research the answer on the internet. ChatGPT, on the other hand, will typically rely on the information that it was trained on (Bard, 2023).

Bal Ram and Pratima Verma (2023) found that ChatGPT was better at generating creative text formats, such as poems, code, scripts, musical pieces, emails, and letters. Google AI Bard was better at answering questions in a comprehensive and informative way, even if the questions were open-ended, challenging, or strange.

Summary

Like ChatGPT, Bard is a conversational AI chatbot that can generate text, translate languages, write different kinds of creative content, and answer your questions in an informative way. Give Bard a prompt or ask it a question and the chatbot can answer it in a surprisingly natural and conversational language. Bard can access the internet to leverage Google search for its responses while ChatGPT can only provide historical content gathered through 2021. It is important to note that Google Bard does not use ChatGPT. Bard uses its own proprietary AI technology.

References

Bal Ram, & Pratima Verma. (2023). Artificial Intelligence AI-based chatbot study of CHATGPT, Google AI Bard, and Baidu AI. World Journal of Advanced Engineering Technology and Sciences, 8(1), 258–261. https://doi.org/10.30574/wjaets.2023.8.1.0045

Bard. (2023, August 15). Differences between Bard and ChatGPT. Retrieved from https://bard.google/

Bard. (2023, August 15). How to use Google Bard. Retrieved from https://bard.google/

Pichai, S. (2023, February 6). An important next step on our AI journey. Google. https://blog.google/intl/en-africa/products/explore-get-answers/an-important-next-step-on-our-ai-journey/

Related Scholarly Articles:

Laato, S., Morschheuser, B., Hamari, J., & Björne, J. (2023). AI-assisted learning with ChatGPT and large language models: Implications for higher education. ResearchGate<. https://www.researchgate.net/publication/370535123_AI-assisted_Learning_with_ChatGPT_and_Large_Language_Models_Implications_for_Higher_Education

Meyer, J. G., Urbanowicz, R. J., Martin, P. C., O’Connor, K., Li, R., Peng, P.-C., Bright, T. J., Tatonetti, N., Won, K. J., Gonzalez-Hernandez, G., & Moore, J. H. (2023). ChatGPT and large language models in academia: Opportunities and challenges. BioData Mining, 16(1). https://doi.org/10.1186/s13040-023-00339-9

___________________________________________________________________________________

Washington, G. (2023, August 31). Bard – Google’s Conversational AI [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Implementing ChatGPT in Online Teaching and Learning

Ready or not, here comes ChatGPT! ChatGPT (Chat Generative Pre-Trained Transformer) is a generative artificial intelligence (AI) chatbot that uses machine learning models to produce human-like text. It can complete sentences, answer questions, generate text, and even hold a conversation with a human user. ChatGPT was trained on a massive amount of text data from the internet and other sources, allowing it to understand and generate responses to a wide variety of topics. As an instructor, you may be curious about how ChatGPT can be utilized in online courses to enhance teaching and learning. Here are some practical tips for implementing ChatGPT:

Virtual Class Discussions: Use ChatGPT as a discussion partner in virtual classes. Students can interact with ChatGPT and engage in meaningful conversations on different topics related to the curriculum. ChatGPT can generate responses, ask questions, and provide additional information to stimulate discussions and encourage critical thinking.

Virtual Office Hours: Use ChatGPT as a virtual assistant during office hours. Students can ask questions, seek clarification, or request assistance from ChatGPT, just like they would with an instructor. ChatGPT can provide quick responses and support students in real time, facilitating a personalized learning experience.

Automated Feedback: Use ChatGPT to provide automated feedback on student assignments or assessments. ChatGPT can generate feedback on written assignments, provide explanations for incorrect answers, and offer suggestions for improvement. This can save time for the instructor while providing timely feedback to students.

Virtual Tutoring: Use ChatGPT as a virtual tutor to provide additional support to students who need extra help. ChatGPT can provide explanations, examples, and practice exercises on specific topics or concepts, catering to the individual needs of students and supplementing the instruction provided by the instructor.

Resource Generator: Use ChatGPT to generate learning resources such as study guides, summaries, or quiz questions. ChatGPT can quickly generate content based on the curriculum or specific learning outcomes, providing students with additional study materials and practice opportunities.

Practice: Use ChatGPT for language practice in online language courses. Students can engage in conversational exchanges with ChatGPT to practice their speaking and writing skills in a supportive and interactive environment. ChatGPT can provide feedback and corrections to help students improve their language proficiency.

Digital Research Assistant: Use ChatGPT as a digital research assistant to help students find relevant information for their projects or assignments. ChatGPT can generate responses to questions, provide summaries of articles or papers, and offer suggestions for credible sources, helping students conduct efficient and effective research.

It is important to provide clear instructions and guidelines to students on how to effectively use ChatGPT as a learning tool, emphasizing responsible and ethical use. Regular monitoring and review of ChatGPT-generated content should be conducted to ensure accuracy and appropriateness. Additionally, instructors should be open to feedback from students and continuously evaluate the effectiveness of ChatGPT in enhancing the online teaching and learning experience.

In conclusion, ChatGPT can be a valuable tool in online teaching and learning, providing opportunities for interactive discussions, personalized feedback, virtual tutoring, resource generation, language practice, and research assistance. By incorporating ChatGPT thoughtfully into online educational settings, instructors can create engaging and innovative learning experiences that enhance student learning outcomes.

Please share your plans, ideas, questions, or concerns about using ChatGPT or other AI in your teaching.

References:

OpenAI. (2022, September 2). About OpenAI. OpenAI. Retrieved January 24, 2023, from https://openai.com/about/.

OpenAI. (2023, April 19). ChatGPT [Computer software]. Retrieved from https://www.openai.com/chatgpt/.

Cooper, G. (2023). Examining science education in CHATGPT: An exploratory study of Generative Artificial Intelligence. Journal of Science Education and Technology. https://doi.org/10.1007/s10956-023-10039-y

Cotton, D. R., Cotton, P. A., & Shipway, J. R. (2023). Chatting and cheating: Ensuring academic integrity in the era of ChatGPT. Innovations in Education and Teaching International, 1–12. https://doi.org/10.1080/14703297.2023.2190148

Mollick, E. R., & Mollick, L. (2022). New modes of learning enabled by AI Chatbots: Three methods and assignments. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.4300783

O’Connor, S., & ChatGPT. (2023). Open artificial intelligence platforms in nursing education: Tools for academic progress or abuse? Nurse Education in Practice, 66, N.PAG. https://doi.org/10.1016/j.nepr.2022.103537

Pavlik, J. V. (2023). Collaborating with ChatGPT: Considering the implications of Generative Artificial Intelligence for Journalism and Media Education. Journalism &amp; Mass Communication Educator, 78(1), 84–93. https://doi.org/10.1177/10776958221149577

___________________________________________________________________________________

Washington, G. (2023, April 20). Implementing ChatGPT in Online Teaching and Learning [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Photo by Rolf van Root on Unsplash

Conversations With ChatGPT

By now, you have likely heard about ChatGPT free version GPT 3.5. Launched in 2022 by OpenAI, Chat Generative Pre-Trained Transformer, commonly called ChatGPT is an artificial intelligence (AI) chatbot. ChatGPT, as a generative AI platform, generates responses to text prompts using its knowledge acquired from machine learning through engagement with the internet. ChatGPT interacts with humans in a conversational way. In this article, the human author’s queries and prompts appear as headings in bold text followed by automated responses from ChatGPT. The automated responses written by ChatGPT appear exactly as presented online. The conversation focuses on AI, ChatGPT, and ChatGPT in education. Citations for two scholarly, peer-reviewed journals are given at the end of the article.

What is ChatGPT?

ChatGPT is a conversational AI language model developed by OpenAI. It is trained on a massive dataset of human text, making it capable of generating human-like responses to a wide range of questions and prompts. ChatGPT can be used to build conversational interfaces like chatbots and virtual assistants, enabling them to engage in natural language conversations with users.

Tell me more

ChatGPT is a transformer-based language model that uses deep learning techniques to generate text based on the input it receives. It is trained on a diverse range of texts, including books, articles, and web pages, giving it a wide range of knowledge and the ability to generate human-like responses to questions.

ChatGPT can be fine-tuned for specific tasks and domains, such as customer service, FAQ answering, or creative writing. It can also generate text in multiple languages, making it a powerful tool for building multilingual conversational AI systems.

ChatGPT has become popular among developers and researchers for its ability to generate high-quality text, making it a popular choice for building conversational AI applications.

Explain how ChatGPT works

ChatGPT works by using a deep learning model called a Transformer, which is trained on a large corpus of text data to generate text that is similar to human writing. The model consists of an encoder and a decoder, which work together to generate a text sequence based on an input prompt.

When the model is given a prompt, the encoder first processes the input and generates a fixed-length representation, or hidden state, that summarizes the input. This hidden state is then passed to the decoder, which uses it to generate the final text output, one word at a time.

At each time step, the decoder considers the previous words generated, the input prompt, and the hidden state generated by the encoder, to predict the next word in the sequence. This process continues until the model generates a stop token or reaches a maximum length, at which point the final output text is returned.

To make the generated text more coherent and realistic, the model is trained with a language modeling objective, which encourages it to generate text that is similar to the training data and to predict the next word in a sentence based on the preceding context.

Overall, ChatGPT works by using a deep learning model to generate text that is similar to human writing, based on an input prompt and its training data.

What are the capabilities of ChatGPT?

ChatGPT has several capabilities, including:

1. Text generation: ChatGPT can generate coherent and coherently written text based on a prompt, making it a popular choice for language generation tasks like chatbots, virtual assistants, and story writing.
2. Conversational AI: ChatGPT can be used to build conversational interfaces, such as chatbots, that can understand and respond to natural language inputs from users.
3. Question answering: ChatGPT can be fine-tuned to answer questions based on a given context or knowledge base, making it a popular choice for building FAQ chatbots and virtual assistants.
4. Text classification: ChatGPT can also be fine-tuned for text classification tasks, such as sentiment analysis or topic classification, by training it to predict a label for a given input text.
5. Multilingual support: ChatGPT can generate text in multiple languages, making it a powerful tool for building multilingual conversational AI systems.

Overall, ChatGPT's capabilities make it a versatile and powerful tool for building AI applications that involve natural language processing and text generation.

What is the impact of ChatGPT on education?

ChatGPT, being an AI language model, has the potential to revolutionize the way people learn and access information. The model's ability to respond to a wide range of questions with coherent and relevant answers can provide students with quick and accurate answers to their questions, reducing the time they spend searching for information. Additionally, ChatGPT can be used to create educational content and interactive learning experiences, making education more engaging and accessible for people of all ages. However, it's important to note that ChatGPT is just a tool and its impact on education will depend on how it's used, integrated into existing educational systems, and supplemented with human teachers and mentors.

What should educators teach students about AI?

Educators should teach students about AI from a multidisciplinary perspective, covering its technical aspects, ethical considerations, and social implications. The following topics can be covered:

1. Technical aspects: How AI works, including machine learning algorithms and neural networks, and their applications in various fields such as computer vision, natural language processing, and robotics.
2. Ethical considerations: The importance of responsible AI development, including data privacy, bias, and transparency.
3. Social implications: The impact of AI on society, including job displacement and the potential for AI to be used for malicious purposes.
4. Critical thinking: Encouraging students to think critically about the information they receive from AI systems, and to understand the limitations and biases of AI.
5. Creative applications: Encouraging students to explore the creative potential of AI, including developing their own AI projects and exploring its use in fields like art and design.

By teaching students about AI in this way, educators can help them to become informed and responsible users of AI technology, and to understand its potential impact on society.

Explain to include ChatGPT

Educators can also include ChatGPT as a teaching tool in their lessons on AI. ChatGPT is a powerful AI language model that can demonstrate the capabilities and limitations of AI technology. Educators can use ChatGPT to:

1. Show how AI can generate human-like responses: By asking ChatGPT questions and demonstrating how it generates answers, educators can show students how AI can mimic human communication and language.
2. Highlight the limitations of AI: By asking ChatGPT questions it can't answer or demonstrating how it can produce biased or incorrect answers, educators can show students the limitations of AI technology and the importance of critical thinking when using AI systems.
3. Foster creative thinking: By using ChatGPT as a tool for creative projects, such as generating poetry or storytelling, educators can encourage students to explore the creative potential of AI.
4. Enhance interactive learning experiences: By incorporating ChatGPT into educational games, simulations, and virtual environments, educators can create engaging and interactive learning experiences for students.

By incorporating ChatGPT into their lessons on AI, educators can provide students with a hands-on, practical experience with AI technology, which can help them to better understand its capabilities and limitations.

What type of assignments can be used to incorporate ChatGPT?

There are several types of assignments that can be used to incorporate ChatGPT into education:

1. Q&A sessions: Students can ask ChatGPT questions on various topics, such as history, science, or current events, and compare its responses to their own understanding of the subject.
2. Chatbot creation: Students can create their own chatbots using tools like OpenAI's GPT-3 and integrate ChatGPT into their chatbots to provide responses.
3. Creative writing: Students can use ChatGPT as a writing tool to generate poetry, short stories, or other forms of creative writing.
4. Critical analysis: Students can analyze the responses generated by ChatGPT and evaluate its accuracy, bias, and limitations.
5. Group projects: Students can work in teams to create interactive games, simulations, or virtual environments that incorporate ChatGPT.

These types of assignments can provide students with hands-on experience using AI technology and help them to understand its potential and limitations. Additionally, incorporating ChatGPT into assignments can make learning more engaging and interactive for students.

How might students use ChatGPT in doing their own academic work?

Students can use ChatGPT in several ways to assist them with their academic work:

1. Research: ChatGPT can provide students with quick and accurate answers to questions they have while conducting research, saving them time and effort.
2. Writing: ChatGPT can be used as a writing tool, helping students generate ideas and outlines for papers, essays, and other academic assignments.
3. Language learning: ChatGPT can assist students in practicing and improving their language skills by providing conversation partners and language-specific responses.
4. Problem solving: ChatGPT can help students solve problems in math and science by providing step-by-step explanations and solutions to problems.
5. Study aids: ChatGPT can be used to generate study aids, such as flashcards, quizzes, and summaries, to help students retain and understand the material they are studying.

It's important to note that while ChatGPT can be a valuable tool for students, it should not be relied upon as the sole source of information or support for academic work. Students should still conduct their own research and engage in critical thinking to fully understand the material they are studying. Additionally, they should also seek help from human teachers and mentors when needed.

Conclusion

In conclusion, ChatGPT is a powerful AI language model with the potential to transform the way people learn and access information. Incorporating ChatGPT into education can make learning more engaging, interactive, and efficient for students. However, it's important to remember that ChatGPT is just a tool and its impact on education will depend on how it's used and integrated into existing educational systems. Educators should aim to teach students about AI from a multidisciplinary perspective, covering its technical aspects, ethical considerations, and social implications, and encourage critical thinking and creative applications. By doing so, students can become informed and responsible users of AI technology and understand its potential impact on society.

Please share your plans, ideas, questions, or concerns about using AI in your teaching. 

References:

OpenAI. (2022). ChatGPT. https://chat.openai.com/chat\

Scholarly (Peer-Reviewed) Journal Articles:

O’Connor, S., & ChatGPT. (2023). Open artificial intelligence platforms in nursing education: Tools for academic progress or abuse? Nurse Education in Practice, 66, N.PAG. https://doi.org/10.1016/j.nepr.2022.103537

Pavlik, J. V. (2023). Collaborating With ChatGPT: Considering the Implications of Generative Artificial Intelligence for Journalism and Media Education. Journalism & Mass Communication Educator, 1. https://doi.org/10.1177/10776958221149577

_________________________________________________________________________

Cite this blog: Washington, G. & ChatGPT. (2023, January 31). Conversations With ChatGPT [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Image by Andrea De Santis on Unsplash

Student-Created Podcasts As An Innovative Approach to Assessments

Typically, podcasts have been used to deliver instructor-created lectures or supplemental course content. Podcasts are audio files that are made available publicly or privately for listening via streaming or download through a range of devices such as laptops and cell phones. This article provides examples of assignments that ask students to produce podcasts as an alternative to traditional assignments.

As a pivot to online teaching during COVID-19, Halabi (2021) described how a student-produced podcast assessment substituted for the final examination in an MBA accounting course. Students were tasked with interviewing a small business owner, entrepreneur, or start-up to create a podcast to help teach or illustrate an accounting concept learned throughout the course. The instructor provided two options for creating the podcast: Kaltura Capture software (supported by the university) and Audacity (not supported by the university). Students also received detailed instructions and requirements of the assessment, a grading rubric, and previous student examples. In addition to creating and submitting the podcast, students created and submitted a one-page description or summary of the podcast. Based on reflections from the instructor and students, the student-produced podcasts provided an efficient learning experience that connected theory to practice while serving as an authentic assessment. Although the traditional accounting assessment was changed due to the COVID-19 pandemic, podcast assignments have ongoing applicability as authentic assessments in future semesters, even for other disciplines.

Using the SAMR (Substitution, Augmentation, Modification, and Redefinition) model, Hitchcock, Sage, Lynch, and Sage (2021), redefined a traditional social work research paper to incorporate a podcast interview. The four social work instructors collaborated to develop, implement, and evaluate a podcast assignment in different sections of practice and policy courses at the undergraduate and graduate levels.  This case study evaluated how podcasting technology contributed to building social work skills in the classroom. It addressed two research questions:

• Can a digital podcast assignment contribute to social work learning outcomes?
• Do students perceive the digital podcast assignment to be as effective as traditional assignments in achieving social work learning outcomes?

Students were asked to create a podcast, 15-20 minutes in length, using an interview or discussion approach, on a topic relevant to the course. The creation process started with a written plan and an interview guide, included a written transcript, and ended with a reflection. Students exchanged their podcasts with each other and provided feedback using the assignment rubric as a guide. Instructors also provided feedback to the students using the same rubric. The instructors found that the podcast assignments contributed to social work learning outcomes and enhanced student learning. Overall, students felt that the podcast assignment was better than traditional classroom assignments, such as writing a paper or completing a PowerPoint presentation.

In summary, podcasting in education is a great way to enhance the learning experience for students. One way to implement podcasts in a course is to modify an existing assessment, wherein students use the audio format of the medium in place of a written paper or presentation. Podcasts expose students to opportunities to use technology and show what they know differently from traditional assignments.

References

Halabi, A. K. (2021). Pivoting authentic assessment to an accounting podcast during COVID-19. Accounting Research Journal, 34(2), 156–168. https://doi.org/10.1108/ARJ-08-2020-0219

Hitchcock, L. I., Sage, T., Lynch, M., & Sage, M. (2021). Podcasting as a Pedagogical Tool for Experiential Learning in Social Work Education. Journal of Teaching in Social Work, 41(2), 172–191. https://doi.org/10.1080/08841233.2021.1897923

_________________________________________________________________________

Cite this blog: Washington, G. (2022, December 31). Student-created podcasts as an innovative approach to assessments [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Photo by Jonathan Velasquez on Unsplash _________________________________________________________________________

Next Blog Article: January 31, 2023

Student-Student Interaction

Student-student interaction is a vital part of any student learning experience whether face-to-face, blended/hybrid, or online. With the increasing use of online course delivery in higher education, this is a perfect time to discuss student-student interaction. According to research, the more that students interact with each other through engagement opportunities fostered by the instructor, the more they get to know and learn from each other.

In a recent case study, Amrullah and Zahratun (2022) explored how students interact with each other in online learning environments. The study was situated in a public university in Indonesia with students participating in the Teaching English for Young Learners online course.  The lecturer designed the course to promote student-student interactions. Students participated in real-time virtual discussions as synchronous meetings to discuss, exchange their ideas, and interact with each other.  The lecturer provided new insight and skills to the students through posted materials. Students engaged in WhatsApp groups and used Moodle as an asynchronous platform to discuss course materials and collaborate on group projects. Students had opportunities to learn from each other, the content, and the lecturer. During assigned synchronous meetings, one group served as the expert for a particular topic. The lecturer encouraged the other groups to raise questions and discuss authentic cases with the expert group. In this sense, the lecturer played “a pivotal role in facilitating students to have effective interactions by providing various activities, prepared materials, and support” (p. 37).

Likewise, Morrison (2021) found that student-student interaction in online courses led to greater student success in overcoming barriers and challenges to online learning. Morrison removed and replaced all quizzes with discussion boards in online courses. Students discussed real-world situations to stimulate authentic and creative social interactions to learn from each other. The credit per discussion board was broken into two parts with the initial response worth 15 points and the response to peers worth 5 points. The module topics were incorporated into the discussion board. Morrison discovered that students preferred the discussion boards to the quizzes and developed a greater sense of an inclusive academic community. In addition, in the public organization course, students worked in groups to create a public sector organization based on the topics covered in the course. For the final assignment, student groups presented their project via video. Real-world application through discussion boards and group projects enhanced the students’ subject mastery and critical thinking skills.

In summary, one way to increase student engagement is through student-student interaction. As educators, you can create opportunities for students to engage with other students. As you explore new possibilities, ask yourself these questions: How can I provide opportunities for students to get to know their classmates throughout the semester or year and not just on day one? How can I create opportunities for student-student interaction through activities, assignments, and instructional materials? What technology will I use, such as discussions in a learning management system, VoiceThread, Flip (previously FlipGrid), or Padlet?

References

Amrullah, & Zahratun N. (2022). Student-student interaction in an online learning during the covid-19 pandemic. Journal of Applied Studies in Language, 6(1), 37–45. https://doi.org/10.31940/jasl.v6i1.446

Morrison, J. S. (2021). Getting to Know You: Student-Faculty Interaction and Student Engagement in Online Courses. Journal of Higher Education Theory & Practice, 21(12), 38–44. https://doi.org/10.33423/jhetp.v21i12.4697

_________________________________________________________________________________

Cite this blog: Washington, G. (2022, August 31). Student-student interaction [Blog post]. Retrieved from https://pedagogybeforetechnology.blogspot.com/

Photo by Maya Maceka on Unsplash