OpenBookQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

AI2_ARC experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

TQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

E-EVAL experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

TQA Accuracy Comparison Chart on different LLM. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

ScienceQA experimental results. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Code interpreter with LLM. by Jin Lu (428513)

“…We evaluated our proposed system on five educational datasets—AI2_ARC, OpenBookQA, E-EVAL, TQA, and ScienceQA—which represent diverse question types and domains. Compared to vanilla Large Language Models (LLMs), our approach combining Retrieval-Augmented Generation (RAG) with Code Interpreters achieved an average accuracy improvement of 10−15 percentage points. …”

Number of tweets collected over time. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Descriptive measures of the dataset. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Corpora from the articles in order of size. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Media information. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Information from interactions. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Table of the database statistical measures. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Tweets information. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Examples of tweets texts (Portuguese). by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Methodological flowchart. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Number of tweets collected per query and type. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Examples of tweets texts (English). by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

Users information. by Sylvia Iasulaitis (8301189)

“…Python algorithms were developed to model each primary collection type. …”

JASPEX model by Olugbenga OLUWAGBEMI (21403187)

“…</p><p dir="ltr">We wrote new sets of python codes and developed python programming codes to rework on the map to generate the coloured map of Southwest Nigeria from the map of Nigeria (which represented the region of our study). …”