Detecting Emotions in Social Media: A Constrained Optimization Approach

Authors: Yichen Wang, Aditya Pal

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we evaluate our model through three diverse real world datasets, and show that it outperforms existing state-of-art methods for emotion detection.
Researcher Affiliation Collaboration Yichen Wang Aditya Pal Georgia Institute of Technology IBM Research Atlanta, GA San Jose, CA yichen.wang@gatech.edu aditya.pal@gmail.com
Pseudocode Yes Algorithm 1 MINIMIZE Ψ 1: Initialize S(0), D(0), u(0), v(0), A(0), B(0) randomly 2: t = 0 3: repeat 4: t = t + 1 5: Compute S(t) using multiplicative rule (Eq 5). 6: Similarly compute D(t), u(t), v(t), A(t), B(t). 7: until Ψ(t 1) Ψ(t) ϵ or t max Iteration 8: return S(t), D(t), u(t), v(t), A(t), B(t)
Open Source Code No The paper does not provide any explicit statements or links indicating that the source code for the methodology is openly available.
Open Datasets Yes Sem Eval2: This dataset consists of 1250 news headlines annotated by human coders on six emotions... http://web.eecs.umich.edu/~mihalcea/downloads.html
Dataset Splits Yes We use 10-fold cross validation to run our experiments and report precision (P), recall (R), and F-score (F).
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU models, CPU types, memory) used to run the experiments.
Software Dependencies No The paper mentions mathematical models and algorithms (e.g., NMF, SVM, multiplicative update rule) but does not specify any software libraries or their version numbers used in the implementation.
Experiment Setup Yes We use cosine similarity between the documents features to compute their topic similarity and set threshold τ=0.8.