arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1305.3932cs.SIcs.HCcs.LG
收藏

用定量置信度推断推文的起源位置

Inferring the Origin Locations of Tweets with Quantitative Confidence

Los Alamos National Laboratory(洛斯阿拉莫斯国家实验室);Illinois Institute of Technology(伊利诺伊理工学院)

Reid Priedhorsky, Aron Culotta, Sara Y. Del Valle

摘要:

社交互联网内容在许多领域发挥着越来越重要的作用,包括公共卫生,灾害管理和政治。然而,它的实用性受到缺少地理信息的限制;例如,不到1.6%的Twitter消息(tweets)包含地理标签。我们提出了一个可扩展的,基于内容的方法来估计推文的位置,使用一种新颖而简单的高斯混合模型的变体。此外,由于现实世界的应用程序依赖于量化的不确定性,这样的估计,我们提出了新的指标的准确性,精度和校准,我们相应地评估我们的方法。对1300万条全球多语言推文的实验表明,我们的方法产生了可靠的、校准良好的结果,与以前的计算密集型方法相比具有竞争力。我们还表明,一个相对较少的训练数据是需要良好的估计(大约30,000推)和模型是相当的时间不变(有效的推比训练集更新许多周)。最后,我们表明,地名和语言的地理足迹小,提供了最有用的位置信号。

英文摘要:

Social Internet content plays an increasingly critical role in many domains, including public health, disaster management, and politics. However, its utility is limited by missing geographic information; for example, fewer than 1.6% of Twitter messages (tweets) contain a geotag. We propose a scalable, content-based approach to estimate the location of tweets using a novel yet simple variant of gaussian mixture models. Further, because real-world applications depend on quantified uncertainty for such estimates, we propose novel metrics of accuracy, precision, and calibration, and we evaluate our approach accordingly. Experiments on 13 million global, comprehensively multi-lingual tweets show that our approach yields reliable, well-calibrated results competitive with previous computationally intensive methods. We also show that a relatively small number of training data are required for good estimates (roughly 30,000 tweets) and models are quite time-invariant (effective on tweets many weeks newer than the training set). Finally, we show that toponyms and languages with small geographic footprint provide the most useful location signals.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑