Identifying Semantic Edit Intentions from Revisions in Wikipedia

By Diyi Yang, Aaron L Halfaker, Robert E. Kraut, Eduard H. Hovy. 2017

94 citations recorded by the source corpus.

Most studies on human editing focus merely on syntactic revision operations, failing to capture the intentions behind revision changes, which are essential for facilitating the single and collaborative writing process. In this work, we develop in collaboration with Wikipedia editors a 13-category taxonomy of the semantic intention behind edits in Wikipedia articles. Using labeled article edits, we build a computational classifier of intentions that achieved a micro-averaged F1 score of 0.621. We use this model to investigate edit intention effectiveness: how different types of edits predict the retention of newcomers and changes in the quality of articles, two key concerns for Wikipedia today. Our analysis shows that the types of edits that users make in their first session predict their subsequent survival as Wikipedia editors, and articles in different stages need different types of edits.

Subfields: Communication, Molecular Biology, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Molecular Biology

In Natural Language Processing

Citations in the corpus

PEER: A Collaborative Language Model (2022, background): “Closely related to our work, Yang et al. (2017) classify edit intentions in Wikipedia’s edit history.”
Get Your Vitamin C! Robust Fact Verification with Contrastive Evidence (2021, methodology): “Naturally, the real Wikipedia revisions we collect mostly describe facts that frequently change over time, or that are prone to mistakes and corrections (such as quantitative values, see Appendix A.1) (Faruqui et al., 2018; Yang et al., 2017).”
Automatically Neutralizing Subjective Bias in Text (2019, methodology): “The Wiki Neutrality Corpus consists of aligned sentences pre and post -neutralization by English Wikipedia editors (Table 1 provided NPOV-related justiﬁcation (Zanzotto and Pennac-chiotti 2010; Recasens, Danescu-Niculescu-Mizil, and Ju-rafsky 2013; Yang et al. 2017).”
Understanding Iterative Revision from Human-Written Text (2022, background): “…focusing largely on sentence-level editing (Faruqui et al., 2018; Botha et al., 2018; Ito et al., 2019; Faltings et al., 2021); (3) developing editing taxonomies within individual domains (e.g. Wikipedia articles, academic writings) (Yang et al., 2017; Zhang et al., 2017; Anthonio et al., 2020).”
Learning to Represent Edits (2018, background): “Autoencoders (see Goodfellow et al. (2016) for an overview) have a long history in machine learning.”
Text Editing by Command (2020, background): “Yang et al. (2017) create 13 edit intention categories, and train a classiﬁer to label revisions according to the categories.”
ORES (2019, methodology): “used Wiki labels and some of our feature extraction systems to build their own models [109].”
Learning to Model Editing Processes (2022, methodology): “In Yang et al. (2017a), they classify 5,777 Wikipedia revisions into 10 intention classes, such as “Clari-fication”, “Vandalism”, and others with each representing a different intention.”