Journal of Digital Information Management Hsuanwei Michelle Chen 13 3 2015 Online recommendations are considered as a useful approach to encourage consumer purchases and drive product sales in e-commerce. This paper uses a multimodal approach to examine the effectiveness of online recommendations using the lenses of econometric modeling and text mining. Applying data on Amazon's 'customers who bought this item also bought' recommendation, commonly referred to as the co-purchase network, this study presents several findings. First, the effects of direct co-purchase recommendations on product sales are essentially strong, regardless of other potential factors that can also affect those sales. Second, the sales of one product can have positive effect on the sales of another, when the latter is suggested in co-purchase recommendations. Moreover, the similarity of the customer base between the two co-purchased products, which can be extracted using text mining from online reviews, will affect that product's sales. This finding leads to the conclusion that online recommendations achieve by recommending related products to like-minded consumers, and that recommendation effect is significant. These results contribute to academics and practitioners by providing clear economic evidence of the value of using text mining approaches for online recommendations.