Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams

Abstract

Time is an important relevance signal when searching streams of social media posts. e distribution of document timestamps from the results of an initial query can be leveraged to infer the distribution of relevant documents, which can then be used to rerank the initial results. Previous experiments have shown that kernel density estimation is a simple yet e ective implementation of this idea. is paper explores an alternative approach to mining temporal signals with recurrent neural networks. Our intuition is that neural networks provide a more expressive framework to capture the temporal coherence of neighboring documents in time. To our knowledge, we are the rst to integrate lexical and temporal signals in an end-to-end neural network architecture, in which existing neural ranking models are used to generate query-document similarity vectors that feed into a bidirectional LSTM layer for temporal modeling. Our results are mixed: existing neural models for document ranking alone yield limited improvements over simple baselines, but the integration of lexical and temporal signals yield signi cant improvements over competitive temporal baselines.

Simple Attention-Based Representation Learning for Ranking Short Social Media Posts

“…Despite a large body of work on neural ranking models for "traditional" ad hoc retrieval over web pages and newswire documents (Huang et al, 2013;Shen et al, 2014;Guo et al, 2016;Xiong et al, 2017;Mitra et al, 2017;Pang et al, 2017;Dai et al, 2018;McDonald et al, 2018), there has been surprisingly little work (Rao et al, 2017) on applying neural networks to searching short social media posts such as tweets on Twitter. Rao et al (2019) identified short document length, informality of language, and heterogeneous relevance signals as main challenges in relevance modeling, and proposed the first neural model specifically designed to handle these characteristics.…”