# The More Similar, the Better? Associations between Latent Semantic Similarity and Emotional Experiences Differ across Conversation Contexts

arXiv: https://arxiv.org/abs/2309.12646 · HTML: https://mlsanity.com/paper/2309.12646/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 80 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Towards General Text Embeddings with Multi-stage Contrastive Learning](https://mlsanity.com/paper/2308.03281/) (2023)
- [MTEB: Massive Text Embedding Benchmark](https://mlsanity.com/paper/2210.07316/) (2022)
- [Evolution of Semantic Similarity -- A Survey](https://mlsanity.com/paper/2004.13820/) (2020)
- [BERT meets LIWC: Exploring State-of-the-Art Language Models for Predicting Communication Behavior in Couples' Conflict Interactions](https://mlsanity.com/paper/2106.01536/) (2021)

## Built on by (most cited first, 1 of 1)

- [ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents](https://mlsanity.com/paper/2605.27240/) (2026)

## Abstract (arXiv)

Latent semantic similarity (LSS) is a measure of the similarity of information exchanges in a conversation. Challenging the assumption that higher LSS bears more positive psychological meaning, we propose that this association might depend on the type of conversation people have. On the one hand, the share-mind perspective would predict that higher LSS should be associated with more positive emotional experiences across the board. The broaden-and-build theory, on the other hand, would predict that higher LSS should be inversely associated with more positive emotional experiences specifically in pleasant conversations. Linear mixed modeling based on conversations among 50 long-term married couples supported the latter prediction. That is, partners experienced greater positive emotions when their overall information exchanges were more dissimilar in pleasant (but not conflict) conversations. This work highlights the importance of context in understanding the emotional correlates of LSS and exemplifies how modern natural language processing tools can be used to evaluate competing theory-driven hypotheses in social psychology.