Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Predicting and Analyzing Language Specificity in Social Media Posts
Authors: Yifan Gao, Yang Zhong, Daniel Preoţiuc-Pietro, Junyi Jessy Li6415-6422
AAAI 2019 | Venue PDF | LLM Run Details | Input Tokens: 16,765 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,231 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We collect a dataset of over 7,000 tweets annotated with specificity on a fine-grained scale. Using this dataset, we train a supervised regression model that accurately estimates specificity in social media posts, reaching a mean absolute error of 0.3578 (for ratings on a scale of 1-5) and 0.73 Pearson correlation, significantly improving over baselines and previous sentence specificity prediction systems. |
| Researcher Affiliation | Collaboration | Yifan Gao, Yang Zhong, Daniel Preot iuc-Pietro, Junyi Jessy Li Department of Mathematics, Department of Linguistics, The University of Texas at Austin {yifan233@,yang.zhong@,jessy@austin.}utexas.edu Bloomberg LP EMAIL |
| Pseudocode | No | The paper describes the model and features but does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our dataset and system are openly available online.2 https://github.com/cs329yangzhong/specificity Twitter |
| Open Datasets | Yes | To this end, we first introduce a large dataset of 7,267 tweets annotated with text specificity on a fine-grained scale of 1-5. ... Our dataset and system are openly available online.2 https://github.com/cs329yangzhong/specificity Twitter |
| Dataset Splits | Yes | We use the dataset described in Section 3 for training (5,767 examples), validation/development (500 examples) and testing (1,000 examples). |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types, or memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper mentions software like 'Scikit-Learn', 'Stanford Name Entity Recognizer', and 'Stanford POS Tagger' but does not specify their version numbers. |
| Experiment Setup | Yes | Specifically, we use Support Vector Regression (SVR) with Radial Basis Function (RBF) kernel3 for sentence specificity prediction. ... The dimension for word embeddings and the number of Brown clusters are 100, tuned on validation set. |