Coming to Grips with Age Prediction on Imbalanced Multimodal Community Question Answering Data

Abstract

For almost every online service, it is fundamental to understand patterns, differences and trends revealed by age demographic analysis—for example, take the discovery of malicious activity, including identity theft, violation of community guidelines and fake profiles. In the particular case of platforms such as Facebook, Twitter and Yahoo! Answers, user demographics have impacts on their revenues and user experience; demographics assist in ensuring that the needs of each cohort are fulfilled via personalizing and contextualizing content. Despite the fact that technology has been made more accessible, thereby becoming evermore prevalent in both personal and professional lives alike, older people continue to trail Gen Z and Millennials in its adoption. This trailing brings about an under-representation that has a harmful influence on the demographic analysis and on supervised machine learning models. To that end, this paper pioneers attempts at examining this and other major challenges facing three distinct modalities when dealing with community question answering (cQA) platforms (i.e., texts, images and metadata). As for textual inputs, we propose an age-batched greedy curriculum learning (AGCL) approach to lessen the effects of their inherent class imbalances. When built on top of FastText shallow neural networks, AGCL achieved an increase of ca. 4% in macro-F1-score with respect to baseline systems (i.e., off-the-shelf deep neural networks). With regard to metadata, our experiments show that random forest classifiers significantly improve their performance when individuals close to generational borders are excluded (up to 20% more accuracy); and by experimenting with neural network-based visual classifiers, we discovered that images are the most challenging modality for age prediction. In fact, it is hard for a visual inspection to connect profile pictures with age cohorts, and there are considerable differences in their group distributions with respect to meta-data and textual inputs. All in all, we envisage that our findings will be highly relevant as guidelines for constructing assorted multimodal supervised models for automatic age recognition across cQA platforms.

Learning from High-Dimensional and Class-Imbalanced Datasets Using Random Forests

“…Although the methodology adopted here is learner-independent, we conducted our study with the Random Forest (RF) classifier [11], which is increasingly being employed in several application scenarios, even in the context of high-dimensional or imbalanced problems (e.g., [12][13][14][15]38,39]). In brief, the RF classifier can be considered as a special case of bagging, an ensemble approach that combines predictions from multiple classifiers More in detail, the ranking-based approach leverages a proper evaluation criterion to weight each single feature based on its relevance to the target class; then, according to their weights, the features are ordered from the most important to the least important, and only a predefined number of the top-ranked features are used for classification.…”

“…Although the methodology adopted here is learner-independent, we conducted our study with the Random Forest (RF) classifier [11], which is increasingly being employed in several application scenarios, even in the context of high-dimensional or imbalanced problems (e.g., [12][13][14][15]38,39]). In brief, the RF classifier can be considered as a special case of bagging, an ensemble approach that combines predictions from multiple classifiers built from different bootstrap samples of the training data.…”

Analysis of community question‐answering issues via machine learning and deep learning: State‐of‐the‐art review

“…This demography analysis can be reported as real concern feeding artificial intelligence in proper exploration within [184]. Relatively, Figueroa et al [185] suggested a multi-modal method for automatic age recognition across CQA platforms that uses text, image, and metadata [186]. Social influence on user's CQA contribution: In a social question-answer community, Dong et al [187] explored the role of social influence on endorsement behaviour.…”

User Demographic Prediction Based on the Fusion of Mobile and Survey Data

“…If demographic prediction can be performed using multi-source data to enrich the data volumes and features, the results will be more certain. Second, although some works do use heterogeneous data-sets from several sources at the same time to train the prediction model, the multi-source data used in these works are merged in a hard-matching method which does not achieve data fusion in the true sense [12], [34], [35], [36], [37], [38], [39], [40], [41], [42], [43], [44], [45]. The hard-matching method refers to extracting users or features that overlap across multiple datasets, and then splicing them together to create a new dataset for model training.…”