When packaging fails in the field, engineers have long relied on lab testing, field trials, and simulation to understand why. But once a product reaches the consumer, that visibility often disappears.
“What we often don’t know from these evaluation methods is: how did the consumer actually experience that failure?” said Michigan State University student Jordan D’Amario during her presentation at ISTA’s TransPack Forum last week. “What part of the package mattered most to them, and which component truly drove that frustration?”
That gap between controlled testing and real-world experience is what D’Amario and her advisor, Dr. Euihark Lee, set out to address with a new AI-driven framework called PackSense.
From lab results to real-world feedback
Traditional packaging evaluation methods remain foundational, but they are inherently limited.
“We rely on three primary approaches: field evaluation, laboratory evaluation, and finite element analysis,” D’Amario said. “They’re foundational and necessary, but they’re often limited to pre-distribution environments.”
Dr. Lee framed the challenge more directly.
“Traditional methods cannot catch up that information well,” he said. “What we are trying to do is… catch what's really happening in the real world that traditional methods cannot catch.”
The idea came from a familiar behavior: reading online reviews.
“Whenever I travel, I always check the hotel reviews,” Lee said. “I get some very meaningful information… why don’t we grab similar idea from the packaging reviews?”
Online reviews, in this sense, become a massive, untapped dataset of post-distribution packaging performance.
Traditional testing methods provide controlled insight—but leave a gap in understanding real-world consumer experience.ISTA, Michigan State's Jordan D'Amario
Turning reviews into structured data
The challenge is that reviews are messy—ranging from detailed narratives to vague complaints.
“Some people say their entire life stories in their reviews, other people are very vague,” D’Amario said.
PackSense applies a combination of rule-based and generative AI to impose structure on that variability.
“We can extract specific components, conditions, severity, and emotions from online reviews,” she said. “So what that means is we can figure out which components of packaging were most damaged… and how consumers react to packaging.”
In the formal framework, that process converts unstructured feedback into labeled data:
- component (pump, bottle, seal)
- condition (leaking, broken, loose)
- severity (cosmetic vs functional failure)
- emotion (frustration, satisfaction, disappointment)
“Instead of just understanding that there was bad packaging, we can understand that it was actually the pump that broke or the closure that was cracked,” D’Amario said.
That shift from general complaint to component-level diagnosis is what makes the data actionable.
What the data shows: functionality drives frustration
In a case study analyzing 369 Amazon reviews of a Tea Tree body wash, the framework identified clear failure patterns.
“The pump was the most frequently reported failure point,” D’Amario said. “It appeared 58 times as broken or not working, and 38 times as leaking, loose, or open.”
The bottle followed closely behind, with structural failures and leakage, while seals played a secondary but still significant role.
Component-level analysis reveals pumps, bottles, and seals as the primary drivers of packaging failure.ISTA, Michigan State's Jordan D'Amario
Just as important as the failures themselves was how consumers reacted to them.
“Broken pumps and leaking bottles were most commonly associated with emotions like frustration and disappointment,” D’Amario said.
In fact, about 25% of consumers who mentioned packaging expressed frustration tied directly to those issues.
That connection between failure and emotion is critical.
“It’s not just that components fail—it’s that certain failures trigger stronger emotional reactions,” she said.
And those reactions often stem from lost functionality.
“If a pump isn’t working… the consumer has to transfer the product to another package,” D’Amario said. “That just adds a step of inconvenience that consumers honestly don’t want to deal with.”
Prioritizing what matters most
By combining frequency of failure with emotional impact, the framework helps identify where redesign efforts should focus.
“When you match that with the components and the conditions… then we can run targeted calculations to really understand where your design priorities should be,” D’Amario said.
The results are often concentrated.
“Pump, bottle, and closure issues account for 83% of defective packages,” she said.
This prioritization changes how packaging teams approach redesign.
“So instead of saying ‘packaging failed,’ we can now say: the pump is the primary driver of functional failure,” D’Amario said.
That level of specificity enables targeted fixes—often without a full redesign.
“It could be a simple fix… maybe you need a stronger adhesive,” she said.
Combining frequency and emotional impact highlights high-priority redesign targets.ISTA, Michigan State University's Jordan D'Amario
A complement, not a replacement
Despite its capabilities, both researchers emphasized that this approach is not meant to replace traditional testing.
“This framework can serve as a scalable complement to traditional testing,” D’Amario said. “It doesn’t replace ISTA lab testing protocols—it extends beyond them.”
Dr. Lee reinforced that distinction.
“Industry standard testing… is very important,” he said. “This consistent testing procedure gives some benefit… to identify if their packaging is working or not.”
Instead, PackSense operates as a post-launch feedback loop.
“We can actually extract hundreds of thousands of the data,” Lee said. “From there we can find out some critical issue that connect to the packaging and then customer usage.”
Closing the loop between design and experience
The broader implication is a tighter connection between packaging design and consumer experience.
“When companies design their packaging with the consumer in mind from the start, that pays off,” D’Amario said.
In one comparison, a more consumer-centric package design generated significantly higher satisfaction scores in reviews.
The takeaway is is that packaging performance is no longer defined solely in the lab or along the supply chain. It is also defined at the moment of use, where it pairs with consumer experience and emotion.
And now, with tools like PackSense, that moment can be measured, structured, and fed back into packaging design.
Matt Reynolds, Packaging World (00:56):
(00:56):
All right. That give me a chance to catch back. Hi, I'm Matt Reynolds, chief editor of Packaging World Magazine, and I'm here in Phoenix today where I saw a fascinating presentation on something called PackSense, which is being put together by Michigan State University as a AI-based, product review-scraping, packaging sentiment evaluator. So I'm here today with Jordan and Dr. Lee. Jordan. Why don't you introduce yourself, Dr. Lee, introduce yourself, whoever wants to go first and then
(00:56):
Jordan D'Amario Student Michigan State University (01:25):
Yeah, so I'm Jordan D'Amario. I'm a student at Michigan State University, so go green. I have been working with Dr. Lee for the past two years or so on this research and now it's kind of coming into fruition and I'm presenting it here today at ISTA.
Matt Reynolds, Packaging World (01:43):
Good. And Dr. Lee, introduce yourself first and what's kind of the genesis, this has to have been going on longer than revealing it today. So what's going on behind the scenes?
Dr. Lee, PhD, Michigan State (01:52):
Okay, so my name is Euihark Lee. I'm a professor from the school of packaging at MSU. So what I usually do is I try to bring some new aspect of the packaging evaluation tool that the traditional method couldn't catch up. So originally I was thinking about a computer simulation in that level, but I realized there's some challenges because computer simulation does not fully represent what the packaging are facing. So then I moved to the database one. So that's how this PackSense project start.
Matt Reynolds, Packaging World (02:24):
Okay. So what problem are you solving with this data? What is the issue in this world that PackSense is going to help address?
Dr. Lee, PhD, Michigan State (02:34):
My understanding is actually if you find out the problem clearly, then finding solution is easy. Most of the case we don't know what's the problem. That's kind of make a finding solution very challenging. So packaging issue is so diverse, so many variations from the material, from the supply chain method and then the way peoples are handled and then traditional method cannot catch up those information well. So what we're trying to do is because my personal experience, because whenever I travel, I love traveling and then whenever I go traveling and then finding a hotel, I always check the reviews and then, okay, because I got some very meaningful information from the hotel reviews and why don't we grab similar idea from the packaging reviews. So that's how these projects start. And then what we are trying to do is because all the reviews are actually real cases, so by extracting some meaningful information from those reviews, we can actually catch what really happening into the real world that traditional [package testing] method cannot catch up. So that's what we are trying to do throughout the review analysis to finding something traditional method cannot find it.
Matt Reynolds, Packaging World (03:46):
Okay. So you're filling a gap that was there between traditional lab testing or field testing and the real world, which we all know behaves differently, but at the same time, these customer reviews, they vary from good, bad, thumbs up, thumbs down to extremely nuanced, to using foul language, to having photos and not having photos. So what are you extracting from these very extremely varied and disparate reviews?
Jordan D'Amario Student Michigan State University (04:15):
I'll take that. Yeah, so like you mentioned, consumer reviews are so varied. Some people say their entire life stories in their reviews, other people are very vague or just basic with their reviews. And what our framework aims to accomplish is to use AI to extract the packaging related reviews. Because believe it or not, consumers do talk about packaging whether they realize it or not. So when we use generative AI and also our rule-based AI models, we can extract specific components, conditions, severity, and emotions from online reviews. So what that means is we can figure out which components of packaging were most damaged, which components of packaging were most affected by the consumer emotions and how strongly were they damaged. So it's kind of two tone in the way where we can understand what kinds of packaging were damaged and we can also understand how consumers react to packaging.
Matt Reynolds, Packaging World (05:13):
Now translate that information, that new data to Proctor and Gamble or Unilever or whomever Kraft, how do they then make that actionable?
Jordan D'Amario Student Michigan State University (05:23):
Yeah, so from a company CPG standpoint, all you would need is your Amazon review page link. And from there what insights you can get is you could understand which components of your packaging were breaking the most. So whether if you have a bottle with a pump, we can understand whether it was the pump that was breaking, the closure, the seal, the actual bottle body that was breaking, and then we can also understand how your consumers reacted to that packaging damage. So from there we got a scale of consumer emotion. So you're
Matt Reynolds, Packaging World (05:58):
Quantifying this,
Jordan D'Amario Student Michigan State University (05:59):
Quantifying that emotion, correct. And the reviews. And when you match that with the components and the conditions that the components experience, then we can run targeted calculations to really understand where your design priorities should be
Matt Reynolds, Packaging World (06:13):
Made, your redesign priorities
(06:14):
Specifically. Okay. Now you had on stage today and maybe we'll be able to show a quick photo, but you had, I don't know if this is a real brand or just like a pilot brand or a beta test kind of thing. I think it was Tea Tree. I know that's a true brand too. Okay. So what were your findings from this? This is a real world. This was something that consumers are actually opening up to varying degrees of satisfaction, let's say. And what did you find? What were you able to glean and extract from reviews from the most sophisticated to the least sophisticated reviews,
Jordan D'Amario Student Michigan State University (06:44):
Photos,
Matt Reynolds, Packaging World (06:45):
Non-photo, that sort of thing. What did this case study tell you?
Jordan D'Amario Student Michigan State University (06:48):
So this case study really demonstrated the importance of having a package that is one, functional. And two, durable, because those are the components that we realize that consumers care about the most. Those are the components. So specifically with the case study, it was the closures, pumps, and the bottles. So again, the components that reduce or impact the functionality, those are the ones that drive the most negative consumer sentiment. So those are going to be the ones that you want to prioritize for redesign.
Matt Reynolds, Packaging World (07:19):
Okay. And then what does that look like? What's the action? Is it keeping the seal unbroken and maybe shipping with the entire closure and pump closure and everything separate that the consumer
Jordan D'Amario Student Michigan State University (07:32):
Then
Matt Reynolds, Packaging World (07:32):
Does it himself?
Jordan D'Amario Student Michigan State University (07:33):
Yeah, so that's one of the ideas. Our program also is able to produce a packaging recommendation that's generated from generative ai, but we engineered a prompt to give those kind of high risk areas. So in that case you can understand, 'okay, if we have this many occurrences of the seal breaking, maybe you need a stronger adhesive, maybe you need to increase the adhesive temperature to make sure it's on there better.' So things like that the generative AI can pull out and give recommendations to. And then it's also able to provide engineering references like ISTA documents, like other case studies that people have done in the past to then kind of help with that ideation and redesign.
Matt Reynolds, Packaging World (08:19):
Okay. Now what it sounds like though is it could be a simple fix that might not require a total redesign, but just moving from adhesive-based to ultrasonic ceiling or something like that. Exactly. Okay, good. Now those are the things that you were hoping to find but kind of extraneously to the study. I think you said there are certain failures or breakages or leakers or so on that really creates a certain emotional response that maybe you weren't expecting. So why don't you walk us through some of the unexpected things on consumer emotion that leaky packages give us all?
Jordan D'Amario Student Michigan State University (08:53):
Yeah, so I would say from our case study we noticed that even though there are some damages with shipping boxes, those typically weren't as common or as frequent. However they still drove negative reactions. So I mean there's no big surprise that if your package gets damaged, consumers are going to be angry about it. But it's that certain failures, drive certain emotions or stronger emotions. So we found kind of like I mentioned earlier, but things that affect the functionality. So for example, if a pump isn't working, all of a sudden the consumer has to take the bottle, transfer the product to another package, and that just adds a step of inconvenience that consumers honestly don't want to deal with. So I would say that was kind of the biggest takeaway is that you really want to focus on certain components that drive the strongest negative reactions to make sure that your or optimizing the most consumer satisfaction,
Matt Reynolds, Packaging World (09:54):
20% of the failures are causing 80% of the angst
Jordan D'Amario Student Michigan State University (09:57):
Or something along
Matt Reynolds, Packaging World (09:58):
Those lines.
Jordan D'Amario Student Michigan State University (09:58):
Yes.
Matt Reynolds, Packaging World (09:59):
So okay, our audience packaging world's audience, largely brand owners, CPGs, some contract packages, some private label folks. So if they're watching, what's one packaging change that they could realistically make? You mentioned pumps and closures, that's mostly for one category, but if you can think of some of your findings, what are some areas that they should really zoom in on?
Dr. Lee, PhD, Michigan State (10:22):
So I think because of the CPG has a lot of variety of the packaging type, it's quite challenging to pick up one specific component. But one thing I can tell is because this tool we actually, the strength of this tool is quantity of the data. So without this tool, I think company need to hire some focus group.
(10:55):
Focus group. I think it's focus group. They have some small focus group and then kind of testing how they are using this packaging, how they apply this type of the features they implement. But in our tool, without this type of focus group (having a focus group is time consuming and then very costly), but we can actually extract hundreds of the thousands of the data and then from there we can find out some critical issue that connect to the packaging and then customer usage. So from there they will identify, oh, this packaging change has been working or is not working. I have some story with one packaging professional, I couldn't go detail, but they actually changed some packaging. And it is for consumer convenience, but they have no idea consumer actually using that feature or not. And then this tool, our tool PackSense can easily capture if consumer really are using those type of tool. So by understanding this packaging component and how these things are working with the consumer, that is one of the strongest benefit of this tool. And then there will be a key point of the or critical point to develop the new packaging.
Matt Reynolds, Packaging World (12:18):
So it's the consumer behavior feedback loop that a brand can learn about how the product is being used and the package is being used or misused out in the wild because some of these bad reviews aren't the brand's fault, it's consumer mishandling. So we're at an ISTA conference. So a lot of what we're talking about are more traditional, whether lab-based or field-based studies. This is by no means meant to replace those. Correct. This is a compliment or an additional tool. So how would you mix those together? How would this augment existing testing?
Dr. Lee, PhD, Michigan State (12:52):
Yeah, so industry standard testing standard is very important because one of the most important thing as a development stage, because this standard give the constant condition. So by changing, so if the testing conditions keep changing, then we don't know because if this packaging working well because of the testing condition change or if the packaging itself has been some update. So this consistent testing procedure gives some benefit of identify if when they develop the packaging, if their packaging is working or not. So I think from the product development side, that will be very helpful. Our end, because we need data, we need a consumer review data, so our end is more likely like a backup data once the product and packaign launches. Ultimately we still can use our tool to see if I need to develop the new shampoo bottle instead of just starting the scratch, I can just scraping other competitor design and then see how different designs are reacting. So that will give some better starting point of that, but to verify that one still is the, or just type of standard testing centers required.
Matt Reynolds, Packaging World (14:04):
Okay. Anything I'm missing? Anything that I should be asking about? Again, my audience, mostly brand owners, CPGs, I believe one of your future employers probably watching right now, sorry, she's spoken for in terms of employment, but what am I missing? What is the big picture takeaway that you want to make sure our viewers hear about or read about?
Jordan D'Amario Student Michigan State University (14:25):
I think just that one of the biggest takeaways is that there's another case study we did for a product that was more consumer-centricly designed for the start and that had a significantly greater increase in consumer satisfaction. So I think that's one of the biggest takeaways here is when companies design their packaging with the consumer in mind from the start, that pays off because consumers end up writing good reviews about how satisfied they are with the package
Matt Reynolds, Packaging World (14:56):
And good reviews that actually generates further purchases.
Jordan D'Amario Student Michigan State University (14:58):
Right, exactly. So it benefits the consumer and it also benefits the business as well. So I think this tool just helps amplify that. And
Matt Reynolds, Packaging World (15:07):
If any of our readers want to find out more, learn more about PAC Sense. Do I have that right? Do they go to the msu.edu? Where do we find more information?
Dr. Lee, PhD, Michigan State (15:16):
Oh, actually we have a separate website
Matt Reynolds, Packaging World (15:18):
Currently
Dr. Lee, PhD, Michigan State (15:18):
Demo version is available, so you cannot actually download your Amazon link, but we already embed one of the demo as an example. So if you go to the PackSense.net, then you should be able to, there's a demo button, then you can see already pre implemented data, you can play with that, what kind of data you can see, what kind of control you can have, those type of things.
Matt Reynolds, Packaging World (15:40):
Okay, great. Well both of you, thank you so much for your time today. We are in the middle of what would be a happy hour downstairs, so we're extracting them from the really fun part to do this. So thanks again for your time, our readers appreciate it. And look for yourselves in the pages of Packaging World Magazine before too long.
