Words are Malleable: Computing Semantic Shifts in Political and Media Discourse
This work addresses the need for analyzing semantic variability beyond just time, offering tools for researchers in computational linguistics and political science to better understand discourse, though it is incremental by extending existing temporal shift methods to other dimensions.
The paper tackles the problem of detecting semantic shifts in words across different viewpoints, such as political parties or time periods, by proposing an approach that learns semantic spaces for each viewpoint and measures shifts using a combination of optimal transformations and neighbor similarity. The result shows that this combined method performs best, capturing meaningful shifts that improve tasks like ideology detection and follow established laws of semantic change.
Recently, researchers started to pay attention to the detection of temporal shifts in the meaning of words. However, most (if not all) of these approaches restricted their efforts to uncovering change over time, thus neglecting other valuable dimensions such as social or political variability. We propose an approach for detecting semantic shifts between different viewpoints--broadly defined as a set of texts that share a specific metadata feature, which can be a time-period, but also a social entity such as a political party. For each viewpoint, we learn a semantic space in which each word is represented as a low dimensional neural embedded vector. The challenge is to compare the meaning of a word in one space to its meaning in another space and measure the size of the semantic shifts. We compare the effectiveness of a measure based on optimal transformations between the two spaces with a measure based on the similarity of the neighbors of the word in the respective spaces. Our experiments demonstrate that the combination of these two performs best. We show that the semantic shifts not only occur over time, but also along different viewpoints in a short period of time. For evaluation, we demonstrate how this approach captures meaningful semantic shifts and can help improve other tasks such as the contrastive viewpoint summarization and ideology detection (measured as classification accuracy) in political texts. We also show that the two laws of semantic change which were empirically shown to hold for temporal shifts also hold for shifts across viewpoints. These laws state that frequent words are less likely to shift meaning while words with many senses are more likely to do so.